Merge pull request #545 from DenisKochetov/feature/update-unet-models

Update UNet models for CharacterGen, Era3D, and Wonder3D
2025-11-17 22:25:56 +06:00 · 2025-11-12 09:27:17 +00:00 · 2025-08-07 18:44:26 +08:00 · 2025-08-07 18:32:52 +08:00 · 2025-08-07 09:48:51 +00:00 · 2025-08-07 17:01:44 +08:00
557 changed files with 321067 additions and 1681 deletions
@@ -7,15 +7,19 @@ on:
    paths:
      - "pyproject.toml"

+permissions:
+  issues: write
+
 jobs:
  publish-node:
    name: Publish Custom Node to registry
    runs-on: ubuntu-latest
+    if: ${{ github.repository_owner == 'MrForExample' }}
    steps:
      - name: Check out code
        uses: actions/checkout@v4
      - name: Publish Custom Node
-        uses: Comfy-Org/publish-node-action@main
+        uses: Comfy-Org/publish-node-action@v1
        with:
          ## Add your own personal access token to your Github Repository secrets and reference it here.
-          personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }}
+          personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }}
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,29 @@
+---
+library_name: diffusers
+pipeline_tag: image-to-image
+license: apache-2.0
+---
+# Model Card for StableNormal
+
+This repository contains the weights of StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal
+
+## Usage
+
+See the Github repository: https://github.com/Stable-X/StableNormal regarding installation instructions.
+
+The model can then be used as follows:
+
+```python
+import torch
+from PIL import Image
+# Load an image
+input_image = Image.open("path/to/your/image.jpg")
+# Create predictor instance
+predictor = torch.hub.load("hugoycj/StableNormal", "StableNormal_turbo", trust_repo=True, yoso_version='yoso-normal-v1-8-1')
+# Generate normal map using alpha channel for masking
+normal_map = predictor(rgba_image, data_type="object")  # Will mask out background, if alpha channel is avalible, else use birefnet
+# Apply the model to the image
+normal_image = predictor(input_image)
+# Save or display the result
+normal_image.save("output/normal_map.png")
+```
@@ -0,0 +1,57 @@
+{
+  "_class_name": "ControlNetVAEModel",
+  "_diffusers_version": "0.28.0",
+  "_name_or_path": "weights/yoso-normal-v1-8-1/controlnet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "class_embed_type": null,
+  "conditioning_channels": 3,
+  "conditioning_embedding_out_channels": [
+    16,
+    32,
+    96,
+    256
+  ],
+  "controlnet_conditioning_channel_order": "rgb",
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "global_pool_conditions": false,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_time_scale_shift": "default",
+  "transformer_layers_per_block": 1,
+  "upcast_attention": true,
+  "use_linear_projection": true
+}
@@ -0,0 +1,250 @@
+# Copyright 2024 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+from dataclasses import dataclass
+from typing import Any, Dict, List, Optional, Tuple, Union
+
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.loaders.single_file_model import FromOriginalModelMixin
+from diffusers.utils import BaseOutput, logging
+from diffusers.models.attention_processor import (
+    ADDED_KV_ATTENTION_PROCESSORS,
+    CROSS_ATTENTION_PROCESSORS,
+    AttentionProcessor,
+    AttnAddedKVProcessor,
+    AttnProcessor,
+)
+from diffusers.models.embeddings import TextImageProjection, TextImageTimeEmbedding, TextTimeEmbedding, TimestepEmbedding, Timesteps
+from diffusers.models.modeling_utils import ModelMixin
+from diffusers.models.unets.unet_2d_blocks import (
+    CrossAttnDownBlock2D,
+    DownBlock2D,
+    UNetMidBlock2D,
+    UNetMidBlock2DCrossAttn,
+    get_down_block,
+)
+from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
+from diffusers.models.controlnet import ControlNetOutput
+from diffusers.models import ControlNetModel
+
+import pdb
+
+
+class ControlNetVAEModel(ControlNetModel):
+    def forward(
+        self,
+        sample: torch.Tensor,
+        timestep: Union[torch.Tensor, float, int],
+        encoder_hidden_states: torch.Tensor,
+        controlnet_cond: torch.Tensor = None,
+        conditioning_scale: float = 1.0,
+        class_labels: Optional[torch.Tensor] = None,
+        timestep_cond: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,
+        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
+        guess_mode: bool = False,
+        return_dict: bool = True,
+    ) -> Union[ControlNetOutput, Tuple[Tuple[torch.Tensor, ...], torch.Tensor]]:
+        """
+        The [`ControlNetVAEModel`] forward method.
+
+        Args:
+            sample (`torch.Tensor`):
+                The noisy input tensor.
+            timestep (`Union[torch.Tensor, float, int]`):
+                The number of timesteps to denoise an input.
+            encoder_hidden_states (`torch.Tensor`):
+                The encoder hidden states.
+            controlnet_cond (`torch.Tensor`):
+                The conditional input tensor of shape `(batch_size, sequence_length, hidden_size)`.
+            conditioning_scale (`float`, defaults to `1.0`):
+                The scale factor for ControlNet outputs.
+            class_labels (`torch.Tensor`, *optional*, defaults to `None`):
+                Optional class labels for conditioning. Their embeddings will be summed with the timestep embeddings.
+            timestep_cond (`torch.Tensor`, *optional*, defaults to `None`):
+                Additional conditional embeddings for timestep. If provided, the embeddings will be summed with the
+                timestep_embedding passed through the `self.time_embedding` layer to obtain the final timestep
+                embeddings.
+            attention_mask (`torch.Tensor`, *optional*, defaults to `None`):
+                An attention mask of shape `(batch, key_tokens)` is applied to `encoder_hidden_states`. If `1` the mask
+                is kept, otherwise if `0` it is discarded. Mask will be converted into a bias, which adds large
+                negative values to the attention scores corresponding to "discard" tokens.
+            added_cond_kwargs (`dict`):
+                Additional conditions for the Stable Diffusion XL UNet.
+            cross_attention_kwargs (`dict[str]`, *optional*, defaults to `None`):
+                A kwargs dictionary that if specified is passed along to the `AttnProcessor`.
+            guess_mode (`bool`, defaults to `False`):
+                In this mode, the ControlNet encoder tries its best to recognize the input content of the input even if
+                you remove all prompts. A `guidance_scale` between 3.0 and 5.0 is recommended.
+            return_dict (`bool`, defaults to `True`):
+                Whether or not to return a [`~models.controlnet.ControlNetOutput`] instead of a plain tuple.
+
+        Returns:
+            [`~models.controlnet.ControlNetOutput`] **or** `tuple`:
+                If `return_dict` is `True`, a [`~models.controlnet.ControlNetOutput`] is returned, otherwise a tuple is
+                returned where the first element is the sample tensor.
+        """
+        # check channel order
+
+
+        channel_order = self.config.controlnet_conditioning_channel_order
+
+        if channel_order == "rgb":
+            # in rgb order by default
+            ...
+        elif channel_order == "bgr":
+            controlnet_cond = torch.flip(controlnet_cond, dims=[1])
+        else:
+            raise ValueError(f"unknown `controlnet_conditioning_channel_order`: {channel_order}")
+
+        # prepare attention_mask
+        if attention_mask is not None:
+            attention_mask = (1 - attention_mask.to(sample.dtype)) * -10000.0
+            attention_mask = attention_mask.unsqueeze(1)
+
+        # 1. time
+        timesteps = timestep
+        if not torch.is_tensor(timesteps):
+            # TODO: this requires sync between CPU and GPU. So try to pass timesteps as tensors if you can
+            # This would be a good case for the `match` statement (Python 3.10+)
+            is_mps = sample.device.type == "mps"
+            if isinstance(timestep, float):
+                dtype = torch.float32 if is_mps else torch.float64
+            else:
+                dtype = torch.int32 if is_mps else torch.int64
+            timesteps = torch.tensor([timesteps], dtype=dtype, device=sample.device)
+        elif len(timesteps.shape) == 0:
+            timesteps = timesteps[None].to(sample.device)
+
+        # broadcast to batch dimension in a way that's compatible with ONNX/Core ML
+        timesteps = timesteps.expand(sample.shape[0])
+
+        t_emb = self.time_proj(timesteps)
+
+        # timesteps does not contain any weights and will always return f32 tensors
+        # but time_embedding might actually be running in fp16. so we need to cast here.
+        # there might be better ways to encapsulate this.
+        t_emb = t_emb.to(dtype=sample.dtype)
+
+        emb = self.time_embedding(t_emb, timestep_cond)
+        aug_emb = None
+
+        if self.class_embedding is not None:
+            if class_labels is None:
+                raise ValueError("class_labels should be provided when num_class_embeds > 0")
+
+            if self.config.class_embed_type == "timestep":
+                class_labels = self.time_proj(class_labels)
+
+            class_emb = self.class_embedding(class_labels).to(dtype=self.dtype)
+            emb = emb + class_emb
+
+        if self.config.addition_embed_type is not None:
+            if self.config.addition_embed_type == "text":
+                aug_emb = self.add_embedding(encoder_hidden_states)
+
+            elif self.config.addition_embed_type == "text_time":
+                if "text_embeds" not in added_cond_kwargs:
+                    raise ValueError(
+                        f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `text_embeds` to be passed in `added_cond_kwargs`"
+                    )
+                text_embeds = added_cond_kwargs.get("text_embeds")
+                if "time_ids" not in added_cond_kwargs:
+                    raise ValueError(
+                        f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `time_ids` to be passed in `added_cond_kwargs`"
+                    )
+                time_ids = added_cond_kwargs.get("time_ids")
+                time_embeds = self.add_time_proj(time_ids.flatten())
+                time_embeds = time_embeds.reshape((text_embeds.shape[0], -1))
+
+                add_embeds = torch.concat([text_embeds, time_embeds], dim=-1)
+                add_embeds = add_embeds.to(emb.dtype)
+                aug_emb = self.add_embedding(add_embeds)
+
+
+        emb = emb + aug_emb if aug_emb is not None else emb
+        # 2. pre-process
+        sample = self.conv_in(sample)
+
+        # 3. down
+        down_block_res_samples = (sample,)
+        for downsample_block in self.down_blocks:
+            if hasattr(downsample_block, "has_cross_attention") and downsample_block.has_cross_attention:
+                sample, res_samples = downsample_block(
+                    hidden_states=sample,
+                    temb=emb,
+                    encoder_hidden_states=encoder_hidden_states,
+                    attention_mask=attention_mask,
+                    cross_attention_kwargs=cross_attention_kwargs,
+                )
+            else:
+                sample, res_samples = downsample_block(hidden_states=sample, temb=emb)
+
+            down_block_res_samples += res_samples
+
+        # 4. mid
+        if self.mid_block is not None:
+            if hasattr(self.mid_block, "has_cross_attention") and self.mid_block.has_cross_attention:
+                sample = self.mid_block(
+                    sample,
+                    emb,
+                    encoder_hidden_states=encoder_hidden_states,
+                    attention_mask=attention_mask,
+                    cross_attention_kwargs=cross_attention_kwargs,
+                )
+            else:
+                sample = self.mid_block(sample, emb)
+
+        # 5. Control net blocks
+
+        controlnet_down_block_res_samples = ()
+
+        # NOTE that controlnet downblock is zeroconv, we discard
+        for down_block_res_sample, controlnet_block in zip(down_block_res_samples, self.controlnet_down_blocks):
+            down_block_res_sample = down_block_res_sample
+            controlnet_down_block_res_samples = controlnet_down_block_res_samples + (down_block_res_sample,)
+
+        down_block_res_samples = controlnet_down_block_res_samples
+
+        mid_block_res_sample = sample
+
+        # 6. scaling
+        if guess_mode and not self.config.global_pool_conditions:
+            scales = torch.logspace(-1, 0, len(down_block_res_samples) + 1, device=sample.device)  # 0.1 to 1.0
+            scales = scales * conditioning_scale
+            down_block_res_samples = [sample * scale for sample, scale in zip(down_block_res_samples, scales)]
+            mid_block_res_sample = mid_block_res_sample * scales[-1]  # last one
+        else:
+            down_block_res_samples = [sample * conditioning_scale for sample in down_block_res_samples]
+            mid_block_res_sample = mid_block_res_sample * conditioning_scale
+
+        if self.config.global_pool_conditions:
+            down_block_res_samples = [
+                torch.mean(sample, dim=(2, 3), keepdim=True) for sample in down_block_res_samples
+            ]
+            mid_block_res_sample = torch.mean(mid_block_res_sample, dim=(2, 3), keepdim=True)
+
+        if not return_dict:
+            return (down_block_res_samples, mid_block_res_sample)
+
+        return ControlNetOutput(
+            down_block_res_samples=down_block_res_samples, mid_block_res_sample=mid_block_res_sample
+        )
+
+
+
@@ -0,0 +1,17 @@
+{
+  "_class_name": "YOSONormalsPipeline",
+  "_diffusers_version": "0.28.0",
+  "controlnet": [
+    "controlnetvae",
+    "ControlNetVAEModel"
+  ],
+  "requires_safety_checker": true,
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}
@@ -0,0 +1,73 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.28.0",
+  "_name_or_path": "weights/yoso-normal-v1-8-1/unet",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": true,
+  "use_linear_projection": true
+}
@@ -0,0 +1,34 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.28.0",
+  "_name_or_path": "weights/yoso-normal-v1-8-1/vae",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,9 @@
+---
+library_name: trellis
+pipeline_tag: image-to-3d
+license: mit
+language:
+- en
+---
+
+An improved normal conditioned version of TRELLIS.
@@ -0,0 +1,17 @@
+{
+    "name": "SLatMeshDecoder",
+    "args": {
+        "resolution": 64,
+        "model_channels": 768,
+        "latent_channels": 8,
+        "num_blocks": 12,
+        "num_heads": 12,
+        "mlp_ratio": 4,
+        "attn_mode": "swin",
+        "window_size": 8,
+        "use_fp16": true,
+        "representation_config": {
+            "use_color": true
+        }
+    }
+}
@@ -0,0 +1,19 @@
+{
+    "name": "SLatFlowModel",
+    "args": {
+        "resolution": 64,
+        "in_channels": 8,
+        "out_channels": 8,
+        "model_channels": 1024,
+        "cond_channels": 1024,
+        "num_blocks": 24,
+        "num_heads": 16,
+        "mlp_ratio": 4,
+        "patch_size": 2,
+        "num_io_res_blocks": 2,
+        "io_block_channels": [128],
+        "pe_mode": "ape",
+        "qk_rms_norm": true,
+        "use_fp16": true
+    }
+}
@@ -0,0 +1,12 @@
+
+{
+    "name": "SparseStructureDecoder",
+    "args": {
+        "out_channels": 1,
+        "latent_channels": 8,
+        "num_res_blocks": 2,
+        "num_res_blocks_middle": 2,
+        "channels": [512, 128, 32],
+        "use_fp16": true
+    }
+}
@@ -0,0 +1,17 @@
+{
+    "name": "SparseStructureFlowModel",
+    "args": {
+        "resolution": 16,
+        "in_channels": 8,
+        "out_channels": 8,
+        "model_channels": 1024,
+        "cond_channels": 1024,
+        "num_blocks": 24,
+        "num_heads": 16,
+        "mlp_ratio": 4,
+        "patch_size": 1,
+        "pe_mode": "ape",
+        "qk_rms_norm": true,
+        "use_fp16": true
+    }
+}
@@ -0,0 +1,58 @@
+{
+    "name": "TrellisImageTo3DPipeline",
+    "args": {
+        "models": {
+            "sparse_structure_decoder": "ckpts/ss_dec_conv3d_16l8_fp16",
+            "sparse_structure_flow_model": "ckpts/ss_flow_normal_dit_L_16l8_fp16",
+            "slat_decoder_mesh": "ckpts/slat_dec_mesh_swin8_B_64l8m256c_fp16",
+            "slat_flow_model": "ckpts/slat_flow_normal_dit_L_64l8p2_fp16"
+        },
+        "sparse_structure_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 25,
+                "cfg_strength": 5.0,
+                "cfg_interval": [0.5, 1.0],
+                "rescale_t": 3.0
+            }
+        },
+        "slat_sampler": {
+            "name": "FlowEulerGuidanceIntervalSampler",
+            "args": {
+                "sigma_min": 1e-5
+            },
+            "params": {
+                "steps": 25,
+                "cfg_strength": 5.0,
+                "cfg_interval": [0.5, 1.0],
+                "rescale_t": 3.0
+            }
+        },
+        "slat_normalization": {
+            "mean": [
+                -2.1687545776367188,
+                -0.004347046371549368,
+                -0.13352349400520325,
+                -0.08418072760105133,
+                -0.5271206498146057,
+                0.7238689064979553,
+                -1.1414450407028198,
+                1.2039363384246826
+            ],
+            "std": [
+                2.377650737762451,
+                2.386378288269043,
+                2.124418020248413,
+                2.1748552322387695,
+                2.663944721221924,
+                2.371192216873169,
+                2.6217446327209473,
+                2.684523105621338
+            ]
+        },
+        "image_cond_model": "dinov2_vitl14_reg"
+    }
+}
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,49 @@
+---
+license: mit
+pipeline_tag: image-to-3d
+tags:
+- triposg
+- 3d-generation
+- rectified-flow
+---
+# TripoSG-scribble - Fast 3D Shape Prototyping with Scribble and Prompt
+
+TripoSG-scribble converts a scribble image and a text prompt to a 3D shape. TripoSG-scribble is a variant of TripoSG. TripoSG is a state-of-the-art image-to-3D generation foundation model that leverages large-scale rectified flow transformers to produce high-fidelity 3D shapes from single images.
+
+## Model Description
+
+### Model Architecture
+
+TripoSG utilizes a novel architecture combining:
+- Rectified Flow (RF) based Transformer for stable, linear trajectory modeling
+- Advanced VAE with SDF-based representation and hybrid geometric supervision
+- Cross-attention mechanism for image feature condition
+- 1.5B parameters operating on 2048 latent tokens
+
+For inference efficiency, TripoSG-scribble is different from TripoSG in:
+- TripoSG-scribble is a CFG-distilled model and should be used with CFG=0
+- TripoSG-scribble is trained with 512 latent tokens
+
+## Intended Uses
+
+This model is designed for:
+- Converting scribble image and text prompt to high-quality 3D meshes
+- Creative and design applications
+- Gaming and VFX asset creation
+- Prototyping and visualization
+
+## Requirements
+
+- CUDA-capable GPU (>8GB VRAM)
+
+## Usage
+
+For detailed usage instructions, please visit our [GitHub repository](https://github.com/VAST-AI-Research/TripoSG).
+
+## About
+
+TripoSG-scribble is developed by [Tripo](https://www.tripo3d.ai), [VAST AI Research](https://github.com/orgs/VAST-AI-Research), pushing the boundaries of 3D Generative AI.
+For more information:
+- [GitHub Repository](https://github.com/VAST-AI-Research/TripoSG)
+- [Paper](https://arxiv.org/abs/2502.06608)
+- [Gradio Demo](https://huggingface.co/spaces/VAST-AI/TripoSG-scribble)
@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}
@@ -0,0 +1,60 @@
+{
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2Model"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "out_features": [
+    "stage24"
+  ],
+  "out_indices": [
+    24
+  ],
+  "patch_size": 14,
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12",
+    "stage13",
+    "stage14",
+    "stage15",
+    "stage16",
+    "stage17",
+    "stage18",
+    "stage19",
+    "stage20",
+    "stage21",
+    "stage22",
+    "stage23",
+    "stage24"
+  ],
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.3",
+  "use_mask_token": true,
+  "use_swiglu_ffn": false
+}
@@ -0,0 +1,32 @@
+{
+  "_class_name": "TripoSGScribblePipeline",
+  "_diffusers_version": "0.33.1",
+  "feature_extractor_dinov2": [
+    "transformers",
+    "BitImageProcessor"
+  ],
+  "image_encoder_dinov2": [
+    "transformers",
+    "Dinov2Model"
+  ],
+  "scheduler": [
+    "TripoSG.schedulers.scheduling_rectified_flow",
+    "RectifiedFlowScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "transformer": [
+    "TripoSG.models.transformers.triposg_transformer",
+    "TripoSGDiTModel"
+  ],
+  "vae": [
+    "TripoSG.models.autoencoders.autoencoder_kl_triposg",
+    "TripoSGVAEModel"
+  ]
+}
@@ -0,0 +1,7 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.33.1",
+  "num_train_timesteps": 1000,
+  "shift": 1,
+  "use_dynamic_shifting": false
+}
@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.3",
+  "vocab_size": 49408
+}
@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}
@@ -0,0 +1,11 @@
+{
+  "_class_name": "TripoSGDiTModel",
+  "_diffusers_version": "0.33.1",
+  "cross_attention_2_dim": 1024,
+  "cross_attention_dim": 768,
+  "in_channels": 64,
+  "num_attention_heads": 16,
+  "num_layers": 21,
+  "use_cross_attention_2": true,
+  "width": 2048
+}
@@ -0,0 +1,14 @@
+{
+  "_class_name": "TripoSGVAEModel",
+  "_diffusers_version": "0.33.1",
+  "embed_frequency": 8,
+  "embed_include_pi": false,
+  "embedding_type": "frequency",
+  "in_channels": 3,
+  "latent_channels": 64,
+  "num_attention_heads": 8,
+  "num_layers_decoder": 16,
+  "num_layers_encoder": 8,
+  "width_decoder": 1024,
+  "width_encoder": 512
+}
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,45 @@
+---
+license: mit
+pipeline_tag: image-to-3d
+tags:
+- triposg
+- 3d-generation
+- rectified-flow
+---
+# TripoSG - High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
+
+TripoSG is a state-of-the-art image-to-3D generation foundation model that leverages large-scale rectified flow transformers to produce high-fidelity 3D shapes from single images.
+
+## Model Description
+
+### Model Architecture
+
+TripoSG utilizes a novel architecture combining:
+- Rectified Flow (RF) based Transformer for stable, linear trajectory modeling
+- Advanced VAE with SDF-based representation and hybrid geometric supervision
+- Cross-attention mechanism for image feature condition
+- 1.5B parameters operating on 2048 latent tokens
+
+## Intended Uses
+
+This model is designed for:
+- Converting single images to high-quality 3D meshes
+- Creative and design applications
+- Gaming and VFX asset creation
+- Prototyping and visualization
+
+## Requirements
+
+- CUDA-capable GPU (>8GB VRAM)
+
+## Usage
+
+For detailed usage instructions, please visit our [GitHub repository](https://github.com/VAST-AI-Research/TripoSG).
+
+## About
+
+TripoSG is developed by [Tripo](https://www.tripo3d.ai), [VAST AI Research](https://github.com/orgs/VAST-AI-Research), pushing the boundaries of 3D Generative AI.
+For more information:
+- [GitHub Repository](https://github.com/VAST-AI-Research/TripoSG)
+- [Paper](https://arxiv.org/abs/2502.06608)
+- [Gradio Demo](https://huggingface.co/spaces/VAST-AI/TripoSG)
@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}
@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "facebook/dinov2-large",
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2Model"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "out_features": [
+    "stage24"
+  ],
+  "out_indices": [
+    24
+  ],
+  "patch_size": 14,
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12",
+    "stage13",
+    "stage14",
+    "stage15",
+    "stage16",
+    "stage17",
+    "stage18",
+    "stage19",
+    "stage20",
+    "stage21",
+    "stage22",
+    "stage23",
+    "stage24"
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "use_swiglu_ffn": false
+}
@@ -0,0 +1,24 @@
+{
+  "_class_name": "TripoSGPipeline",
+  "_diffusers_version": "0.30.3",
+  "feature_extractor_dinov2": [
+    "transformers",
+    "BitImageProcessor"
+  ],
+  "image_encoder_dinov2": [
+    "transformers",
+    "Dinov2Model"
+  ],
+  "scheduler": [
+    "TripoSG.schedulers.scheduling_rectified_flow",
+    "RectifiedFlowScheduler"
+  ],
+  "transformer": [
+    "TripoSG.models.transformers.triposg_transformer",
+    "TripoSGDiTModel"
+  ],
+  "vae": [
+    "TripoSG.models.autoencoders.autoencoder_kl_triposg",
+    "TripoSGVAEModel"
+  ]
+}
@@ -0,0 +1,7 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.30.3",
+  "num_train_timesteps": 1000,
+  "shift": 1,
+  "use_dynamic_shifting": false
+}
@@ -0,0 +1,9 @@
+{
+  "_class_name": "TripoSGDiTModel",
+  "_diffusers_version": "0.30.3",
+  "cross_attention_dim": 1024,
+  "in_channels": 64,
+  "num_attention_heads": 16,
+  "num_layers": 21,
+  "width": 2048
+}
@@ -0,0 +1,14 @@
+{
+  "_class_name": "Tripo2VAEModel",
+  "_diffusers_version": "0.30.3",
+  "embed_frequency": 8,
+  "embed_include_pi": false,
+  "embedding_type": "frequency",
+  "in_channels": 3,
+  "latent_channels": 64,
+  "num_attention_heads": 8,
+  "num_layers_decoder": 16,
+  "num_layers_encoder": 8,
+  "width_decoder": 1024,
+  "width_encoder": 512
+}
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,16 @@
+---
+library_name: trellis
+pipeline_tag: image-to-3d
+license: mit
+language:
+- en
+---
+# TRELLIS Image Large
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+The image conditioned version of TRELLIS, a large 3D genetive model. It was introduced in the paper [Structured 3D Latents for Scalable and Versatile 3D Generation](https://huggingface.co/papers/2412.01506).
+
+Project page: https://trellis3d.github.io/
+
+Code: https://github.com/Microsoft/TRELLIS
@@ -1,224 +0,0 @@
---
-library_name: hunyuan3d-2.0
-license: other
-license_name: tencent-hunyuan-community
-license_link: https://huggingface.co/tencent/Hunyuan3D-2/blob/main/LICENSE.txt
-language:
-  - en
-  - zh
-tags:
-  - image-to-3d
-  - text-to-3d
-pipeline_tag: image-to-3d
---
-
-<p align="center">
-  <img src="./assets/images/teaser.jpg">
-</p>
-
-<div align="center">
-  <a href=https://3d.hunyuan.tencent.com target="_blank"><img src=https://img.shields.io/badge/Hunyuan3D-black.svg?logo=homepage height=22px></a>
-  <a href=https://huggingface.co/spaces/tencent/Hunyuan3D-2  target="_blank"><img src=https://img.shields.io/badge/%F0%9F%A4%97%20Demo-276cb4.svg height=22px></a>
-  <a href=https://huggingface.co/tencent/Hunyuan3D-2 target="_blank"><img src=https://img.shields.io/badge/%F0%9F%A4%97%20Models-d96902.svg height=22px></a>
-  <a href=https://3d-models.hunyuan.tencent.com/ target="_blank"><img src= https://img.shields.io/badge/Page-bb8a2e.svg?logo=github height=22px></a>
-<a href=https://discord.gg/GuaWYwzKbX target="_blank"><img src= https://img.shields.io/badge/Discord-white.svg?logo=discord height=22px></a>
-    <a href=https://github.com/Tencent/Hunyuan3D-2/blob/main/assets/report/Tencent_Hunyuan3D_2_0.pdf target="_blank"><img src=https://img.shields.io/badge/Report-b5212f.svg?logo=arxiv height=22px></a>
-</div>
-
-
-[//]: # (  <a href=# target="_blank"><img src=https://img.shields.io/badge/Report-b5212f.svg?logo=arxiv height=22px></a>)
-
-[//]: # (  <a href=# target="_blank"><img src= https://img.shields.io/badge/Colab-8f2628.svg?logo=googlecolab height=22px></a>)
-
-[//]: # (  <a href="#"><img alt="PyPI - Downloads" src="https://img.shields.io/pypi/v/mulankit?logo=pypi"  height=22px></a>)
-
-<br>
-<p align="center">
-“ Living out everyone’s imagination on creating and manipulating 3D assets.”
-</p>
-
-This repository contains the models of the paper [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://huggingface.co/papers/2501.12202).
-For code and more details on how to use it, refer to the [Github repository](https://github.com/Tencent/Hunyuan3D-2).
-
-## 🔥 News
-
- Jan 21, 2025: 💬 Release [Hunyuan3D 2.0](https://huggingface.co/spaces/tencent/Hunyuan3D-2). Please give it a try!
-
-## **Abstract**
-
-We present Hunyuan3D 2.0, an advanced large-scale 3D synthesis system for generating high-resolution textured 3D assets.
-This system includes two foundation components: a large-scale shape generation model - Hunyuan3D-DiT, and a large-scale
-texture synthesis model - Hunyuan3D-Paint.
-The shape generative model, built on a scalable flow-based diffusion transformer, aims to create geometry that properly
-aligns with a given condition image, laying a solid foundation for downstream applications.
-The texture synthesis model, benefiting from strong geometric and diffusion priors, produces high-resolution and vibrant
-texture maps for either generated or hand-crafted meshes.
-Furthermore, we build Hunyuan3D-Studio - a versatile, user-friendly production platform that simplifies the re-creation
-process of 3D assets. It allows both professional and amateur users to manipulate or even animate their meshes
-efficiently.
-We systematically evaluate our models, showing that Hunyuan3D 2.0 outperforms previous state-of-the-art models,
-including the open-source models and closed-source models in geometry details, condition alignment, texture quality, and
-e.t.c.
-
-<p align="center">
-  <img src="assets/images/system.jpg">
-</p>
-
-## ☯️ **Hunyuan3D 2.0**
-
-### Architecture
-
-Hunyuan3D 2.0 features a two-stage generation pipeline, starting with the creation of a bare mesh, followed by the
-synthesis of a texture map for that mesh. This strategy is effective for decoupling the difficulties of shape and
-texture generation and also provides flexibility for texturing either generated or handcrafted meshes.
-
-<p align="left">
-  <img src="assets/images/arch.jpg">
-</p>
-
-### Performance
-
-We have evaluated Hunyuan3D 2.0 with other open-source as well as close-source 3d-generation methods.
-The numerical results indicate that Hunyuan3D 2.0 surpasses all baselines in the quality of generated textured 3D assets
-and the condition following ability.
-
-| Model                   | CMMD(⬇)   | FID_CLIP(⬇) | FID(⬇)      | CLIP-score(⬆) |
-|-------------------------|-----------|-------------|-------------|---------------|
-| Top Open-source Model1  | 3.591     | 54.639      | 289.287     | 0.787         |
-| Top Close-source Model1 | 3.600     | 55.866      | 305.922     | 0.779         |
-| Top Close-source Model2 | 3.368     | 49.744      | 294.628     | 0.806         |
-| Top Close-source Model3 | 3.218     | 51.574      | 295.691     | 0.799         |
-| Hunyuan3D 2.0           | **3.193** | **49.165**  | **282.429** | **0.809**     |
-
-Generation results of Hunyuan3D 2.0:
-<p align="left">
-  <img src="assets/images/e2e-1.gif"  height=300>
-  <img src="assets/images/e2e-2.gif"  height=300>
-</p>
-
-### Pretrained Models
-
-| Model                | Date       | Huggingface                                            |
-|----------------------|------------|--------------------------------------------------------| 
-| Hunyuan3D-DiT-v2-0   | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2) |
-| Hunyuan3D-Paint-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2) |
-| Hunyuan3D-Delight-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2/tree/main/hunyuan3d-delight-v2-0) |
-
-## 🤗 Get Started with Hunyuan3D 2.0
-
-You may follow the next steps to use Hunyuan3D 2.0 via code or the Gradio App.
-
-### Install Requirements
-
-Please install Pytorch via the [official](https://pytorch.org/) site. Then install the other requirements via
-
-```bash
-pip install -r requirements.txt
-# for texture
-cd hy3dgen/texgen/custom_rasterizer
-python3 setup.py install
-cd ../../..
-cd hy3dgen/texgen/differentiable_renderer
-bash compile_mesh_painter.sh OR python3 setup.py install (on Windows)
-```
-
-### API Usage
-
-We designed a diffusers-like API to use our shape generation model - Hunyuan3D-DiT and texture synthesis model -
-Hunyuan3D-Paint.
-
-You could assess **Hunyuan3D-DiT** via:
-
-```python
-from hy3dgen.shapegen import Hunyuan3DDiTFlowMatchingPipeline
-
-pipeline = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained('tencent/Hunyuan3D-2')
-mesh = pipeline(image='assets/demo.png')[0]
-```
-
-The output mesh is a [trimesh object](https://trimesh.org/trimesh.html), which you could save to glb/obj (or other
-format) file.
-
-For **Hunyuan3D-Paint**, do the following:
-
-```python
-from hy3dgen.texgen import Hunyuan3DPaintPipeline
-from hy3dgen.shapegen import Hunyuan3DDiTFlowMatchingPipeline
-
-# let's generate a mesh first
-pipeline = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained('tencent/Hunyuan3D-2')
-mesh = pipeline(image='assets/demo.png')[0]
-
-pipeline = Hunyuan3DPaintPipeline.from_pretrained('tencent/Hunyuan3D-2')
-mesh = pipeline(mesh, image='assets/demo.png')
-```
-
-Please visit [minimal_demo.py](minimal_demo.py) for more advanced usage, such as **text to 3D** and **texture generation
-for handcrafted mesh**.
-
-### Gradio App
-
-You could also host a [Gradio](https://www.gradio.app/) App in your own computer via:
-
-```bash
-pip3 install gradio==3.39.0
-python3 gradio_app.py
-```
-
-Don't forget to visit [Hunyuan3D](https://3d.hunyuan.tencent.com) for quick use, if you don't want to host yourself.
-
-## 📑 Open-Source Plan
-
- [x] Inference Code
- [x] Model Checkpoints
- [x] Technical Report
- [ ] ComfyUI
- [ ] TensorRT Version
-
-## 🔗 BibTeX
-
-If you found this repository helpful, please cite our report:
-
-```bibtex
-@misc{hunyuan3d22025tencent,
-    title={Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation},
-    author={Tencent Hunyuan3D Team},
-    year={2025},
-    eprint={2501.12202},
-    archivePrefix={arXiv},
-    primaryClass={cs.CV}
-}
-
-@misc{yang2024tencent,
-    title={Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation},
-    author={Tencent Hunyuan3D Team},
-    year={2024},
-    eprint={2411.02293},
-    archivePrefix={arXiv},
-    primaryClass={cs.CV}
-}
-```
-
-## Community Resources
-
-Thanks for the contributions of community members, here we have these great extensions of Hunyuan3D 2.0:
-
- [ComfyUI-Hunyuan3DWrapper](https://github.com/kijai/ComfyUI-Hunyuan3DWrapper)
- [Hunyuan3D-2-for-windows](https://github.com/sdbds/Hunyuan3D-2-for-windows)
- [📦 A bundle for running on Windows | 整合包](https://github.com/YanWenKun/Comfy3D-WinPortable/releases/tag/r8-hunyuan3d2)
-
-## Acknowledgements
-
-We would like to thank the contributors to
-the [DINOv2](https://github.com/facebookresearch/dinov2), [Stable Diffusion](https://github.com/Stability-AI/stablediffusion), [FLUX](https://github.com/black-forest-labs/flux), [diffusers](https://github.com/huggingface/diffusers)
-and [HuggingFace](https://huggingface.co) repositories, for their open research and exploration.
-
-## Star History
-
-<a href="https://star-history.com/#Tencent/Hunyuan3D-2&Date">
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=Tencent/Hunyuan3D-2&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=Tencent/Hunyuan3D-2&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=Tencent/Hunyuan3D-2&type=Date" />
- </picture>
-</a>
@@ -0,0 +1,69 @@
+model:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.Hunyuan3DDiT
+  params:
+    in_channels: 64
+    context_in_dim: 1536
+    hidden_size: 1024
+    mlp_ratio: 4.0
+    num_heads: 16
+    depth: 16
+    depth_single_blocks: 32
+    axes_dim: [ 64 ]
+    theta: 10000
+    qkv_bias: true
+    guidance_embed: true
+
+vae:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+  params:
+    num_latents: 3072
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 0.9990943042622529
+
+conditioner:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.SingleImageEncoder
+  params:
+    main_image_encoder:
+      type: DinoImageEncoder # dino giant
+      kwargs:
+        config:
+          attention_probs_dropout_prob: 0.0
+          drop_path_rate: 0.0
+          hidden_act: gelu
+          hidden_dropout_prob: 0.0
+          hidden_size: 1536
+          image_size: 518
+          initializer_range: 0.02
+          layer_norm_eps: 1.e-6
+          layerscale_value: 1.0
+          mlp_ratio: 4
+          model_type: dinov2
+          num_attention_heads: 24
+          num_channels: 3
+          num_hidden_layers: 40
+          patch_size: 14
+          qkv_bias: true
+          torch_dtype: float32
+          use_swiglu_ffn: true
+        image_size: 518
+
+scheduler:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.schedulers.FlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+
+image_processor:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.preprocessors.ImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,70 @@
+model:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.Hunyuan3DDiT
+  params:
+    in_channels: 64
+    context_in_dim: 1536
+    hidden_size: 1024
+    mlp_ratio: 4.0
+    num_heads: 16
+    depth: 16
+    depth_single_blocks: 32
+    axes_dim: [ 64 ]
+    theta: 10000
+    qkv_bias: true
+    guidance_embed: true
+
+vae:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+  params:
+    num_latents: 3072
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 0.9990943042622529
+
+conditioner:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.SingleImageEncoder
+  params:
+    main_image_encoder:
+      type: DinoImageEncoder # dino giant
+      kwargs:
+        config:
+          attention_probs_dropout_prob: 0.0
+          drop_path_rate: 0.0
+          hidden_act: gelu
+          hidden_dropout_prob: 0.0
+          hidden_size: 1536
+          image_size: 518
+          initializer_range: 0.02
+          layer_norm_eps: 1.e-6
+          layerscale_value: 1.0
+          mlp_ratio: 4
+          model_type: dinov2
+          num_attention_heads: 24
+          num_channels: 3
+          num_hidden_layers: 40
+          patch_size: 14
+          qkv_bias: true
+          torch_dtype: float32
+          use_swiglu_ffn: true
+        image_size: 518
+
+scheduler:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.schedulers.ConsistencyFlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+    pcm_timesteps: 100
+
+image_processor:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.preprocessors.ImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,53 @@
+---
+license: openrail++
+tags:
+- stable-diffusion
+- text-to-image
+---
+
+# SD v2.1-base with Zero Terminal SNR (LAION Aesthetic 6+)
+
+This model is used in [Diffusion Model with Perceptual Loss](https://arxiv.org/abs/2401.00110) paper as the MSE baseline.
+
+This model is trained using zero terminal SNR schedule following [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/abs/2305.08891) paper on LAION aesthetic 6+ data.
+
+This model is finetuned from [stabilityai/stable-diffusion-2-1-base](https://huggingface.co/stabilityai/stable-diffusion-2-1-base).
+
+This model is meant for research demonstration, not for production use.
+
+## Usage
+
+```python
+from diffusers import StableDiffusionPipeline
+prompt = "A young girl smiling"
+pipe = StableDiffusionPipeline.from_pretrained("ByteDance/sd2.1-base-zsnr-laionaes6").to("cuda")
+pipe(prompt, guidance_scale=7.5, guidance_rescale=0.7).images[0].save("out.jpg")
+```
+
+## Related Models
+
+* [bytedance/sd2.1-base-zsnr-laionaes5](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes5)
+* [bytedance/sd2.1-base-zsnr-laionaes6](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes6)
+* [bytedance/sd2.1-base-zsnr-laionaes6-perceptual](https://huggingface.co/ByteDance/sd2.1-base-zsnr-laionaes6-perceptual)
+
+
+## Cite as
+```
+@misc{lin2024diffusion,
+      title={Diffusion Model with Perceptual Loss}, 
+      author={Shanchuan Lin and Xiao Yang},
+      year={2024},
+      eprint={2401.00110},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+
+@misc{lin2023common,
+      title={Common Diffusion Noise Schedules and Sample Steps are Flawed}, 
+      author={Shanchuan Lin and Bingchen Liu and Jiashi Li and Xiao Yang},
+      year={2023},
+      eprint={2305.08891},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```
@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}
@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "D:\\.cache\\huggingface\\hub\\models--sudo-ai--zero123plus-v1.1\\snapshots\\36df7de980afd15f80b2e1a4e9a920d7020e2654\\vision_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0"
+}
@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}
@@ -0,0 +1,37 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.23.1",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ],
+  "unet": [
+    "modules",
+    "UNet2p5DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}
@@ -0,0 +1,15 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.23.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "set_alpha_to_one": true,
+  "steps_offset": 1,
+  "trained_betas": null,
+  "timestep_spacing": "trailing",
+  "rescale_betas_zero_snr": true
+}
@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "vocab_size": 49408
+}
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "stabilityai/stable-diffusion-2",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
@@ -0,0 +1,45 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "use_linear_projection": true
+}
@@ -0,0 +1,610 @@
+# Open Source Model Licensed under the Apache License Version 2.0
+# and Other Licenses of the Third-Party Components therein:
+# The below Model in this distribution may have been modified by THL A29 Limited
+# ("Tencent Modifications"). All Tencent Modifications are Copyright (C) 2024 THL A29 Limited.
+
+# Copyright (C) 2024 THL A29 Limited, a Tencent company.  All rights reserved.
+# The below software and/or models in this distribution may have been
+# modified by THL A29 Limited ("Tencent Modifications").
+# All Tencent Modifications are Copyright (C) THL A29 Limited.
+
+# Hunyuan 3D is licensed under the TENCENT HUNYUAN NON-COMMERCIAL LICENSE AGREEMENT
+# except for the third-party components listed below.
+# Hunyuan 3D does not impose any additional limitations beyond what is outlined
+# in the repsective licenses of these third-party components.
+# Users must comply with all terms and conditions of original licenses of these third-party
+# components and must ensure that the usage of the third party components adheres to
+# all relevant laws and regulations.
+
+# For avoidance of doubts, Hunyuan 3D means the large language models and
+# their software and algorithms, including trained model weights, parameters (including
+# optimizer states), machine-learning model code, inference-enabling code, training-enabling code,
+# fine-tuning enabling code and other elements of the foregoing made publicly available
+# by Tencent in accordance with TENCENT HUNYUAN COMMUNITY LICENSE AGREEMENT.
+
+import copy
+import json
+import os
+from typing import Any, Dict, List, Optional, Tuple, Union
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from diffusers.models import UNet2DConditionModel
+from diffusers.models.attention_processor import Attention
+from diffusers.models.transformers.transformer_2d import BasicTransformerBlock
+from einops import rearrange
+
+
+def _chunked_feed_forward(ff: nn.Module, hidden_states: torch.Tensor, chunk_dim: int, chunk_size: int):
+    # "feed_forward_chunk_size" can be used to save memory
+    if hidden_states.shape[chunk_dim] % chunk_size != 0:
+        raise ValueError(
+            f"`hidden_states` dimension to be chunked: {hidden_states.shape[chunk_dim]}"
+            f"has to be divisible by chunk size: {chunk_size}."
+            f" Make sure to set an appropriate `chunk_size` when calling `unet.enable_forward_chunking`."
+        )
+
+    num_chunks = hidden_states.shape[chunk_dim] // chunk_size
+    ff_output = torch.cat(
+        [ff(hid_slice) for hid_slice in hidden_states.chunk(num_chunks, dim=chunk_dim)],
+        dim=chunk_dim,
+    )
+    return ff_output
+
+
+class Basic2p5DTransformerBlock(torch.nn.Module):
+    def __init__(self, transformer: BasicTransformerBlock, layer_name, use_ma=True, use_ra=True, is_turbo=False) -> None:
+        super().__init__()
+        self.transformer = transformer
+        self.layer_name = layer_name
+        self.use_ma = use_ma
+        self.use_ra = use_ra
+        self.is_turbo = is_turbo
+
+        # multiview attn
+        if self.use_ma:
+            self.attn_multiview = Attention(
+                query_dim=self.dim,
+                heads=self.num_attention_heads,
+                dim_head=self.attention_head_dim,
+                dropout=self.dropout,
+                bias=self.attention_bias,
+                cross_attention_dim=None,
+                upcast_attention=self.attn1.upcast_attention,
+                out_bias=True,
+            )
+
+        # ref attn
+        if self.use_ra:
+            self.attn_refview = Attention(
+                query_dim=self.dim,
+                heads=self.num_attention_heads,
+                dim_head=self.attention_head_dim,
+                dropout=self.dropout,
+                bias=self.attention_bias,
+                cross_attention_dim=None,
+                upcast_attention=self.attn1.upcast_attention,
+                out_bias=True,
+            )
+        if self.is_turbo:
+            self._initialize_attn_weights()
+
+    def _initialize_attn_weights(self):
+
+        if self.use_ma:
+            self.attn_multiview.load_state_dict(self.attn1.state_dict()) 
+            with torch.no_grad():
+                for layer in self.attn_multiview.to_out:
+                    for param in layer.parameters():
+                        param.zero_()
+        if self.use_ra:
+            self.attn_refview.load_state_dict(self.attn1.state_dict()) 
+            with torch.no_grad():
+                for layer in self.attn_refview.to_out:
+                    for param in layer.parameters():
+                        param.zero_()
+
+    def __getattr__(self, name: str):
+        try:
+            return super().__getattr__(name)
+        except AttributeError:
+            return getattr(self.transformer, name)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        attention_mask: Optional[torch.Tensor] = None,
+        encoder_hidden_states: Optional[torch.Tensor] = None,
+        encoder_attention_mask: Optional[torch.Tensor] = None,
+        timestep: Optional[torch.LongTensor] = None,
+        cross_attention_kwargs: Dict[str, Any] = None,
+        class_labels: Optional[torch.LongTensor] = None,
+        added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,
+    ) -> torch.Tensor:
+
+        # Notice that normalization is always applied before the real computation in the following blocks.
+        # 0. Self-Attention
+        batch_size = hidden_states.shape[0]
+
+        cross_attention_kwargs = cross_attention_kwargs.copy() if cross_attention_kwargs is not None else {}
+        num_in_batch = cross_attention_kwargs.pop('num_in_batch', 1)
+        mode = cross_attention_kwargs.pop('mode', None)
+        if not self.is_turbo:
+            mva_scale = cross_attention_kwargs.pop('mva_scale', 1.0)
+            ref_scale = cross_attention_kwargs.pop('ref_scale', 1.0)
+        else:
+            position_attn_mask = cross_attention_kwargs.pop("position_attn_mask", None)
+            position_voxel_indices = cross_attention_kwargs.pop("position_voxel_indices", None)
+            mva_scale = 1.0
+            ref_scale = 1.0
+            
+        condition_embed_dict = cross_attention_kwargs.pop("condition_embed_dict", None)
+
+        if self.norm_type == "ada_norm":
+            norm_hidden_states = self.norm1(hidden_states, timestep)
+        elif self.norm_type == "ada_norm_zero":
+            norm_hidden_states, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.norm1(
+                hidden_states, timestep, class_labels, hidden_dtype=hidden_states.dtype
+            )
+        elif self.norm_type in ["layer_norm", "layer_norm_i2vgen"]:
+            norm_hidden_states = self.norm1(hidden_states)
+        elif self.norm_type == "ada_norm_continuous":
+            norm_hidden_states = self.norm1(hidden_states, added_cond_kwargs["pooled_text_emb"])
+        elif self.norm_type == "ada_norm_single":
+            shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = (
+                self.scale_shift_table[None] + timestep.reshape(batch_size, 6, -1)
+            ).chunk(6, dim=1)
+            norm_hidden_states = self.norm1(hidden_states)
+            norm_hidden_states = norm_hidden_states * (1 + scale_msa) + shift_msa
+        else:
+            raise ValueError("Incorrect norm used")
+
+        if self.pos_embed is not None:
+            norm_hidden_states = self.pos_embed(norm_hidden_states)
+
+        # 1. Prepare GLIGEN inputs
+        cross_attention_kwargs = cross_attention_kwargs.copy() if cross_attention_kwargs is not None else {}
+        gligen_kwargs = cross_attention_kwargs.pop("gligen", None)
+
+        attn_output = self.attn1(
+            norm_hidden_states,
+            encoder_hidden_states=encoder_hidden_states if self.only_cross_attention else None,
+            attention_mask=attention_mask,
+            **cross_attention_kwargs,
+        )
+
+        if self.norm_type == "ada_norm_zero":
+            attn_output = gate_msa.unsqueeze(1) * attn_output
+        elif self.norm_type == "ada_norm_single":
+            attn_output = gate_msa * attn_output
+
+        hidden_states = attn_output + hidden_states
+        if hidden_states.ndim == 4:
+            hidden_states = hidden_states.squeeze(1)
+
+        # 1.2 Reference Attention
+        if 'w' in mode:
+            condition_embed_dict[self.layer_name] = rearrange(
+                norm_hidden_states, '(b n) l c -> b (n l) c',
+                n=num_in_batch
+            )  # B, (N L), C
+
+        if 'r' in mode and self.use_ra:
+            condition_embed = condition_embed_dict[self.layer_name].unsqueeze(1).repeat(1, num_in_batch, 1,
+                                                                                        1)  # B N L C
+            condition_embed = rearrange(condition_embed, 'b n l c -> (b n) l c')
+
+            attn_output = self.attn_refview(
+                norm_hidden_states,
+                encoder_hidden_states=condition_embed,
+                attention_mask=None,
+                **cross_attention_kwargs
+            )
+            if not self.is_turbo:
+                ref_scale_timing = ref_scale
+                if isinstance(ref_scale, torch.Tensor):
+                    ref_scale_timing = ref_scale.unsqueeze(1).repeat(1, num_in_batch).view(-1)
+                    for _ in range(attn_output.ndim - 1):
+                        ref_scale_timing = ref_scale_timing.unsqueeze(-1)
+                        
+            hidden_states = ref_scale_timing * attn_output + hidden_states
+
+            if hidden_states.ndim == 4:
+                hidden_states = hidden_states.squeeze(1)
+
+        # 1.3 Multiview Attention
+        if num_in_batch > 1 and self.use_ma:
+            multivew_hidden_states = rearrange(norm_hidden_states, '(b n) l c -> b (n l) c', n=num_in_batch)
+
+            if self.is_turbo:
+                position_mask = None
+                if position_attn_mask is not None:
+                    if multivew_hidden_states.shape[1] in position_attn_mask:
+                        position_mask = position_attn_mask[multivew_hidden_states.shape[1]]
+                position_indices = None
+                if position_voxel_indices is not None:
+                    if multivew_hidden_states.shape[1] in position_voxel_indices:
+                        position_indices = position_voxel_indices[multivew_hidden_states.shape[1]]
+                attn_output = self.attn_multiview(
+                    multivew_hidden_states,
+                    encoder_hidden_states=multivew_hidden_states,
+                    attention_mask=position_mask,
+                    position_indices=position_indices,
+                    **cross_attention_kwargs
+                )
+            else:
+                attn_output = self.attn_multiview(
+                    multivew_hidden_states,
+                    encoder_hidden_states=multivew_hidden_states,
+                    **cross_attention_kwargs
+                )
+
+            attn_output = rearrange(attn_output, 'b (n l) c -> (b n) l c', n=num_in_batch)
+            
+            hidden_states = mva_scale * attn_output + hidden_states
+            if hidden_states.ndim == 4:
+                hidden_states = hidden_states.squeeze(1)
+
+        # 1.2 GLIGEN Control
+        if gligen_kwargs is not None:
+            hidden_states = self.fuser(hidden_states, gligen_kwargs["objs"])
+
+        # 3. Cross-Attention
+        if self.attn2 is not None:
+            if self.norm_type == "ada_norm":
+                norm_hidden_states = self.norm2(hidden_states, timestep)
+            elif self.norm_type in ["ada_norm_zero", "layer_norm", "layer_norm_i2vgen"]:
+                norm_hidden_states = self.norm2(hidden_states)
+            elif self.norm_type == "ada_norm_single":
+                # For PixArt norm2 isn't applied here:
+                # https://github.com/PixArt-alpha/PixArt-alpha/blob/0f55e922376d8b797edd44d25d0e7464b260dcab/diffusion/model/nets/PixArtMS.py#L70C1-L76C103
+                norm_hidden_states = hidden_states
+            elif self.norm_type == "ada_norm_continuous":
+                norm_hidden_states = self.norm2(hidden_states, added_cond_kwargs["pooled_text_emb"])
+            else:
+                raise ValueError("Incorrect norm")
+
+            if self.pos_embed is not None and self.norm_type != "ada_norm_single":
+                norm_hidden_states = self.pos_embed(norm_hidden_states)
+
+            attn_output = self.attn2(
+                norm_hidden_states,
+                encoder_hidden_states=encoder_hidden_states,
+                attention_mask=encoder_attention_mask,
+                **cross_attention_kwargs,
+            )
+
+            hidden_states = attn_output + hidden_states
+
+        # 4. Feed-forward
+        # i2vgen doesn't have this norm 🤷‍♂️
+        if self.norm_type == "ada_norm_continuous":
+            norm_hidden_states = self.norm3(hidden_states, added_cond_kwargs["pooled_text_emb"])
+        elif not self.norm_type == "ada_norm_single":
+            norm_hidden_states = self.norm3(hidden_states)
+
+        if self.norm_type == "ada_norm_zero":
+            norm_hidden_states = norm_hidden_states * (1 + scale_mlp[:, None]) + shift_mlp[:, None]
+
+        if self.norm_type == "ada_norm_single":
+            norm_hidden_states = self.norm2(hidden_states)
+            norm_hidden_states = norm_hidden_states * (1 + scale_mlp) + shift_mlp
+
+        if self._chunk_size is not None:
+            # "feed_forward_chunk_size" can be used to save memory
+            ff_output = _chunked_feed_forward(self.ff, norm_hidden_states, self._chunk_dim, self._chunk_size)
+        else:
+            ff_output = self.ff(norm_hidden_states)
+
+        if self.norm_type == "ada_norm_zero":
+            ff_output = gate_mlp.unsqueeze(1) * ff_output
+        elif self.norm_type == "ada_norm_single":
+            ff_output = gate_mlp * ff_output
+
+        hidden_states = ff_output + hidden_states
+        if hidden_states.ndim == 4:
+            hidden_states = hidden_states.squeeze(1)
+
+        return hidden_states
+
+@torch.no_grad()
+def compute_voxel_grid_mask(position, grid_resolution=8):
+
+    position = position.half()    
+    B,N,_,H,W = position.shape
+    assert H%grid_resolution==0 and W%grid_resolution==0
+
+    valid_mask = (position != 1).all(dim=2, keepdim=True)
+    valid_mask = valid_mask.expand_as(position)
+    position[valid_mask==False] = 0
+
+    
+    position = rearrange(
+        position,
+        'b n c (num_h grid_h) (num_w grid_w) -> b n num_h num_w c grid_h grid_w', 
+        num_h=grid_resolution, num_w=grid_resolution
+    )
+    valid_mask = rearrange(
+        valid_mask, 
+        'b n c (num_h grid_h) (num_w grid_w) -> b n num_h num_w c grid_h grid_w', 
+        num_h=grid_resolution, num_w=grid_resolution
+    )
+
+    grid_position = position.sum(dim=(-2, -1))
+    count_masked = valid_mask.sum(dim=(-2, -1))
+
+    grid_position = grid_position / count_masked.clamp(min=1)
+    grid_position[count_masked<5] = 0
+
+    grid_position = grid_position.permute(0,1,4,2,3)
+    grid_position = rearrange(grid_position, 'b n c h w -> b n (h w) c')
+
+    grid_position_expanded_1 = grid_position.unsqueeze(2).unsqueeze(4)  # 形状变为 B, N, 1, L, 1, 3
+    grid_position_expanded_2 = grid_position.unsqueeze(1).unsqueeze(3)  # 形状变为 B, 1, N, 1, L, 3
+
+    # 计算欧氏距离
+    distances = torch.norm(grid_position_expanded_1 - grid_position_expanded_2, dim=-1)  # 形状为 B, N, N, L, L
+
+    weights = distances
+    grid_distance = 1.73/grid_resolution
+    
+    #weights = weights*-32
+    #weights = weights.clamp(min=-10000.0)
+    
+    weights = weights< grid_distance
+
+    return weights
+    
+def compute_multi_resolution_mask(position_maps, grid_resolutions=[32, 16, 8]):
+    position_attn_mask = {}
+    with torch.no_grad():
+        for grid_resolution in grid_resolutions:
+            position_mask = compute_voxel_grid_mask(position_maps, grid_resolution)
+            position_mask = rearrange(position_mask, 'b ni nj li lj -> b (ni li) (nj lj)')
+            position_attn_mask[position_mask.shape[1]] = position_mask
+    return position_attn_mask
+
+@torch.no_grad()
+def compute_discrete_voxel_indice(position, grid_resolution=8, voxel_resolution=128):
+
+    position = position.half()    
+    B,N,_,H,W = position.shape
+    assert H%grid_resolution==0 and W%grid_resolution==0
+
+    valid_mask = (position != 1).all(dim=2, keepdim=True)
+    valid_mask = valid_mask.expand_as(position)
+    position[valid_mask==False] = 0
+    
+    position = rearrange(
+        position, 
+        'b n c (num_h grid_h) (num_w grid_w) -> b n num_h num_w c grid_h grid_w', 
+        num_h=grid_resolution, num_w=grid_resolution
+    )
+    valid_mask = rearrange(
+        valid_mask, 
+        'b n c (num_h grid_h) (num_w grid_w) -> b n num_h num_w c grid_h grid_w', 
+        num_h=grid_resolution, num_w=grid_resolution
+    )
+
+    grid_position = position.sum(dim=(-2, -1))
+    count_masked = valid_mask.sum(dim=(-2, -1))
+
+    grid_position = grid_position / count_masked.clamp(min=1)
+    grid_position[count_masked<5] = 0
+
+    grid_position = grid_position.permute(0,1,4,2,3).clamp(0, 1) # B N C H W
+    voxel_indices = grid_position * (voxel_resolution - 1)
+    voxel_indices = torch.round(voxel_indices).long()
+    return voxel_indices
+    
+def compute_multi_resolution_discrete_voxel_indice(
+    position_maps, 
+    grid_resolutions=[64, 32, 16, 8], 
+    voxel_resolutions=[512, 256, 128, 64]
+):
+    voxel_indices = {}
+    with torch.no_grad():
+        for grid_resolution, voxel_resolution in zip(grid_resolutions, voxel_resolutions):
+            voxel_indice = compute_discrete_voxel_indice(position_maps, grid_resolution, voxel_resolution)
+            voxel_indice = rearrange(voxel_indice, 'b n c h w -> b (n h w) c')
+            voxel_indices[voxel_indice.shape[1]] = {'voxel_indices':voxel_indice, 'voxel_resolution':voxel_resolution}
+    return voxel_indices
+
+class UNet2p5DConditionModel(torch.nn.Module):
+    def __init__(self, unet: UNet2DConditionModel) -> None:
+        super().__init__()
+        self.unet = unet
+
+        self.use_ma = True
+        self.use_ra = True
+        self.use_camera_embedding = True
+        self.use_dual_stream = True
+        self.is_turbo = False
+
+        if self.use_dual_stream:
+            self.unet_dual = copy.deepcopy(unet)
+            self.init_attention(self.unet_dual)
+        self.init_attention(self.unet, use_ma=self.use_ma, use_ra=self.use_ra, is_turbo=self.is_turbo)
+        self.init_condition()
+        self.init_camera_embedding()
+
+    @staticmethod
+    def from_pretrained(pretrained_model_name_or_path, **kwargs):
+        torch_dtype = kwargs.pop('torch_dtype', torch.float32)
+        config_path = os.path.join(pretrained_model_name_or_path, 'config.json')
+        unet_ckpt_path = os.path.join(pretrained_model_name_or_path, 'diffusion_pytorch_model.bin')
+        with open(config_path, 'r', encoding='utf-8') as file:
+            config = json.load(file)
+        unet = UNet2DConditionModel(**config)
+        unet = UNet2p5DConditionModel(unet)
+        unet_ckpt = torch.load(unet_ckpt_path, map_location='cpu', weights_only=True)
+        unet.load_state_dict(unet_ckpt, strict=True)
+        unet = unet.to(torch_dtype)
+        return unet
+
+    def init_condition(self):
+        self.unet.conv_in = torch.nn.Conv2d(
+            12,
+            self.unet.conv_in.out_channels,
+            kernel_size=self.unet.conv_in.kernel_size,
+            stride=self.unet.conv_in.stride,
+            padding=self.unet.conv_in.padding,
+            dilation=self.unet.conv_in.dilation,
+            groups=self.unet.conv_in.groups,
+            bias=self.unet.conv_in.bias is not None)
+
+        self.unet.learned_text_clip_gen = nn.Parameter(torch.randn(1, 77, 1024))
+        self.unet.learned_text_clip_ref = nn.Parameter(torch.randn(1, 77, 1024))
+
+    def init_camera_embedding(self):
+
+        if self.use_camera_embedding:
+            time_embed_dim = 1280
+            self.max_num_ref_image = 5
+            self.max_num_gen_image = 12 * 3 + 4 * 2
+            self.unet.class_embedding = nn.Embedding(self.max_num_ref_image + self.max_num_gen_image, time_embed_dim)
+
+    def init_attention(self, unet, use_ma=False, use_ra=False, is_turbo=False):
+
+        for down_block_i, down_block in enumerate(unet.down_blocks):
+            if hasattr(down_block, "has_cross_attention") and down_block.has_cross_attention:
+                for attn_i, attn in enumerate(down_block.attentions):
+                    for transformer_i, transformer in enumerate(attn.transformer_blocks):
+                        if isinstance(transformer, BasicTransformerBlock):
+                            attn.transformer_blocks[transformer_i] = Basic2p5DTransformerBlock(
+                                transformer,
+                                f'down_{down_block_i}_{attn_i}_{transformer_i}',
+                                use_ma, use_ra, is_turbo
+                            )
+
+        if hasattr(unet.mid_block, "has_cross_attention") and unet.mid_block.has_cross_attention:
+            for attn_i, attn in enumerate(unet.mid_block.attentions):
+                for transformer_i, transformer in enumerate(attn.transformer_blocks):
+                    if isinstance(transformer, BasicTransformerBlock):
+                        attn.transformer_blocks[transformer_i] = Basic2p5DTransformerBlock(
+                            transformer,
+                            f'mid_{attn_i}_{transformer_i}',
+                            use_ma, use_ra, is_turbo
+                        )
+
+        for up_block_i, up_block in enumerate(unet.up_blocks):
+            if hasattr(up_block, "has_cross_attention") and up_block.has_cross_attention:
+                for attn_i, attn in enumerate(up_block.attentions):
+                    for transformer_i, transformer in enumerate(attn.transformer_blocks):
+                        if isinstance(transformer, BasicTransformerBlock):
+                            attn.transformer_blocks[transformer_i] = Basic2p5DTransformerBlock(
+                                transformer,
+                                f'up_{up_block_i}_{attn_i}_{transformer_i}',
+                                use_ma, use_ra, is_turbo
+                            )
+
+    def __getattr__(self, name: str):
+        try:
+            return super().__getattr__(name)
+        except AttributeError:
+            return getattr(self.unet, name)
+
+    def forward(
+        self, sample, timestep, encoder_hidden_states,
+        *args, down_intrablock_additional_residuals=None,
+        down_block_res_samples=None, mid_block_res_sample=None,
+        **cached_condition,
+    ):
+        B, N_gen, _, H, W = sample.shape
+        assert H == W
+
+        if self.use_camera_embedding:
+            camera_info_gen = cached_condition['camera_info_gen'] + self.max_num_ref_image
+            camera_info_gen = rearrange(camera_info_gen, 'b n -> (b n)')
+        else:
+            camera_info_gen = None
+
+        sample = [sample]
+        if 'normal_imgs' in cached_condition:
+            sample.append(cached_condition["normal_imgs"])
+        if 'position_imgs' in cached_condition:
+            sample.append(cached_condition["position_imgs"])
+        sample = torch.cat(sample, dim=2)
+
+        sample = rearrange(sample, 'b n c h w -> (b n) c h w')
+
+        encoder_hidden_states_gen = encoder_hidden_states.unsqueeze(1).repeat(1, N_gen, 1, 1)
+        encoder_hidden_states_gen = rearrange(encoder_hidden_states_gen, 'b n l c -> (b n) l c')
+
+        if self.use_ra:
+            if 'condition_embed_dict' in cached_condition:
+                condition_embed_dict = cached_condition['condition_embed_dict']
+            else:
+                condition_embed_dict = {}
+                ref_latents = cached_condition['ref_latents']
+                N_ref = ref_latents.shape[1]
+                if self.use_camera_embedding:
+                    camera_info_ref = cached_condition['camera_info_ref']
+                    camera_info_ref = rearrange(camera_info_ref, 'b n -> (b n)')
+                else:
+                    camera_info_ref = None
+
+                ref_latents = rearrange(ref_latents, 'b n c h w -> (b n) c h w')
+
+                encoder_hidden_states_ref = self.unet.learned_text_clip_ref.unsqueeze(1).repeat(B, N_ref, 1, 1)
+                encoder_hidden_states_ref = rearrange(encoder_hidden_states_ref, 'b n l c -> (b n) l c')
+
+                noisy_ref_latents = ref_latents
+                timestep_ref = 0
+
+                if self.use_dual_stream:
+                    unet_ref = self.unet_dual
+                else:
+                    unet_ref = self.unet
+                unet_ref(
+                    noisy_ref_latents, timestep_ref,
+                    encoder_hidden_states=encoder_hidden_states_ref,
+                    class_labels=camera_info_ref,
+                    # **kwargs
+                    return_dict=False,
+                    cross_attention_kwargs={
+                        'mode': 'w', 'num_in_batch': N_ref,
+                        'condition_embed_dict': condition_embed_dict},
+                )
+                cached_condition['condition_embed_dict'] = condition_embed_dict
+        else:
+            condition_embed_dict = None
+
+        mva_scale = cached_condition.get('mva_scale', 1.0)
+        ref_scale = cached_condition.get('ref_scale', 1.0)
+
+        if self.is_turbo:
+            cross_attention_kwargs_ = {
+                'mode': 'r', 'num_in_batch': N_gen,
+                'condition_embed_dict': condition_embed_dict,
+                'position_attn_mask':position_attn_mask, 
+                'position_voxel_indices':position_voxel_indices,
+                'mva_scale': mva_scale,
+                'ref_scale': ref_scale,
+            }
+        else:
+            cross_attention_kwargs_ = {
+                'mode': 'r', 'num_in_batch': N_gen,
+                'condition_embed_dict': condition_embed_dict,
+                'mva_scale': mva_scale,
+                'ref_scale': ref_scale,
+            }
+        return self.unet(
+            sample, timestep,
+            encoder_hidden_states_gen, *args,
+            class_labels=camera_info_gen,
+            down_intrablock_additional_residuals=[
+                sample.to(dtype=self.unet.dtype) for sample in down_intrablock_additional_residuals
+            ] if down_intrablock_additional_residuals is not None else None,
+            down_block_additional_residuals=[
+                sample.to(dtype=self.unet.dtype) for sample in down_block_res_samples
+            ] if down_block_res_samples is not None else None,
+            mid_block_additional_residual=(
+                mid_block_res_sample.to(dtype=self.unet.dtype)
+                if mid_block_res_sample is not None else None
+            ),
+            return_dict=False,
+            cross_attention_kwargs=cross_attention_kwargs_,
+        )
+
@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}
@@ -0,0 +1,15 @@
+target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+params:
+  num_latents: 3072
+  embed_dim: 64
+  num_freqs: 8
+  include_pi: false
+  heads: 16
+  width: 1024
+  num_decoder_layers: 16
+  qkv_bias: false
+  qk_norm: true
+  scale_factor: 0.9990943042622529
+  geo_decoder_mlp_expand_ratio: 1
+  geo_decoder_downsample_ratio: 2
+  geo_decoder_ln_post: false
@@ -0,0 +1,15 @@
+target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+params:
+  num_latents: 3072
+  embed_dim: 64
+  num_freqs: 8
+  include_pi: false
+  heads: 16
+  width: 1024
+  num_decoder_layers: 16
+  qkv_bias: false
+  qk_norm: true
+  scale_factor: 0.9990943042622529
+  geo_decoder_mlp_expand_ratio: 4
+  geo_decoder_downsample_ratio: 1
+  geo_decoder_ln_post: true
@@ -0,0 +1,82 @@
+model:
+  target: hy3dshape.models.denoisers.hunyuandit.HunYuanDiTPlain
+  params:
+    input_size: &num_latents 4096
+    in_channels: 64
+    hidden_size: 2048
+    context_dim: 1024
+    depth: 21
+    num_heads: 16
+    qk_norm: true
+    text_len: 1370
+    with_decoupled_ca: false
+    use_attention_pooling: false
+    qk_norm_type: 'rms'
+    qkv_bias: false
+    use_pos_emb: false
+    num_moe_layers: 6
+    num_experts: 8
+    moe_top_k: 2
+
+vae:
+  target: hy3dshape.models.autoencoders.ShapeVAE
+  params:
+    num_latents: *num_latents
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_encoder_layers: 8
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 1.0039506158752403
+    geo_decoder_mlp_expand_ratio: 4
+    geo_decoder_downsample_ratio: 1
+    geo_decoder_ln_post: true
+    point_feats: 4
+    pc_size: 81920
+    pc_sharpedge_size: 0
+
+conditioner:
+  target: hy3dshape.models.conditioner.SingleImageEncoder
+  params:
+    main_image_encoder:
+        type: DinoImageEncoder # dino large
+        kwargs:
+            config:
+              attention_probs_dropout_prob: 0.0
+              drop_path_rate: 0.0
+              hidden_act: gelu
+              hidden_dropout_prob: 0.0
+              hidden_size: 1024
+              image_size: 518
+              initializer_range: 0.02
+              layer_norm_eps: 1.e-6
+              layerscale_value: 1.0
+              mlp_ratio: 4
+              model_type: dinov2
+              num_attention_heads: 16
+              num_channels: 3
+              num_hidden_layers: 24
+              patch_size: 14
+              qkv_bias: true
+              torch_dtype: float32
+              use_swiglu_ffn: false
+            image_size: 518
+            use_cls_token: true
+
+scheduler:
+  target: hy3dshape.schedulers.FlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+
+image_processor:
+  target: hy3dshape.preprocessors.ImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: hy3dshape.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}
@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "vision_encoder",
+  "architectures": [
+    "CLIPVisionModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "image_size": 224,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 32,
+  "patch_size": 14,
+  "projection_dim": 1024,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.0"
+}
@@ -0,0 +1,37 @@
+{
+  "_class_name": "HunyuanPaintPipeline",
+  "_diffusers_version": "0.24.0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "modules",
+    "UNet2p5DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "image_encoder": [
+    "transformers",
+    "CLIPVisionModelWithProjection"
+  ]
+}
@@ -0,0 +1,15 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.23.1",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "set_alpha_to_one": true,
+  "steps_offset": 1,
+  "trained_betas": null,
+  "timestep_spacing": "trailing",
+  "rescale_betas_zero_snr": true
+}
@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "stabilityai/stable-diffusion-2",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.0.dev0",
+  "vocab_size": 49408
+}
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "stabilityai/stable-diffusion-2",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
@@ -0,0 +1,45 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "use_linear_projection": true
+}
@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.0.dev0",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}
@@ -0,0 +1,19 @@
+target: hy3dshape.models.ShapeVAE
+params:
+  num_latents: 4096
+  embed_dim: 64
+  num_freqs: 8
+  include_pi: false
+  heads: 16
+  width: 1024
+  num_encoder_layers: 8
+  num_decoder_layers: 16
+  qkv_bias: false
+  qk_norm: true
+  scale_factor: 1.0039506158752403
+  geo_decoder_mlp_expand_ratio: 4
+  geo_decoder_downsample_ratio: 1
+  geo_decoder_ln_post: true
+  point_feats: 4
+  pc_size: 81920
+  pc_sharpedge_size: 0
@@ -0,0 +1,69 @@
+model:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.Hunyuan3DDiT
+  params:
+    in_channels: 64
+    context_in_dim: 1536
+    hidden_size: 1024
+    mlp_ratio: 4.0
+    num_heads: 16
+    depth: 8
+    depth_single_blocks: 16
+    axes_dim: [ 64 ]
+    theta: 10000
+    qkv_bias: true
+    guidance_embed: true
+
+vae:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+  params:
+    num_latents: 512
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 1.0188137142395404
+
+conditioner:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.SingleImageEncoder
+  params:
+    main_image_encoder:
+      type: DinoImageEncoder # dino giant
+      kwargs:
+        config:
+          attention_probs_dropout_prob: 0.0
+          drop_path_rate: 0.0
+          hidden_act: gelu
+          hidden_dropout_prob: 0.0
+          hidden_size: 1536
+          image_size: 518
+          initializer_range: 0.02
+          layer_norm_eps: 1.e-6
+          layerscale_value: 1.0
+          mlp_ratio: 4
+          model_type: dinov2
+          num_attention_heads: 24
+          num_channels: 3
+          num_hidden_layers: 40
+          patch_size: 14
+          qkv_bias: true
+          torch_dtype: float32
+          use_swiglu_ffn: true
+        image_size: 518
+
+scheduler:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.schedulers.FlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+
+image_processor:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.preprocessors.ImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,70 @@
+model:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.Hunyuan3DDiT
+  params:
+    in_channels: 64
+    context_in_dim: 1536
+    hidden_size: 1024
+    mlp_ratio: 4.0
+    num_heads: 16
+    depth: 8
+    depth_single_blocks: 16
+    axes_dim: [ 64 ]
+    theta: 10000
+    qkv_bias: true
+    guidance_embed: true
+
+vae:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+  params:
+    num_latents: 3072
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 1.0188137142395404
+
+conditioner:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.SingleImageEncoder
+  params:
+    main_image_encoder:
+      type: DinoImageEncoder # dino giant
+      kwargs:
+        config:
+          attention_probs_dropout_prob: 0.0
+          drop_path_rate: 0.0
+          hidden_act: gelu
+          hidden_dropout_prob: 0.0
+          hidden_size: 1536
+          image_size: 518
+          initializer_range: 0.02
+          layer_norm_eps: 1.e-6
+          layerscale_value: 1.0
+          mlp_ratio: 4
+          model_type: dinov2
+          num_attention_heads: 24
+          num_channels: 3
+          num_hidden_layers: 40
+          patch_size: 14
+          qkv_bias: true
+          torch_dtype: float32
+          use_swiglu_ffn: true
+        image_size: 1022
+
+scheduler:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.schedulers.ConsistencyFlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+    pcm_timesteps: 100
+
+image_processor:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.preprocessors.ImageProcessorV2
+  params:
+    size: 1022
+    border_ratio: 0.15
+
+pipeline:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,69 @@
+model:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.Hunyuan3DDiT
+  params:
+    in_channels: 64
+    context_in_dim: 1536
+    hidden_size: 1024
+    mlp_ratio: 4.0
+    num_heads: 16
+    depth: 8
+    depth_single_blocks: 16
+    axes_dim: [ 64 ]
+    theta: 10000
+    qkv_bias: true
+    guidance_embed: false
+
+vae:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+  params:
+    num_latents: 512
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 1.0188137142395404
+
+conditioner:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.SingleImageEncoder
+  params:
+    main_image_encoder:
+      type: DinoImageEncoder # dino giant
+      kwargs:
+        config:
+          attention_probs_dropout_prob: 0.0
+          drop_path_rate: 0.0
+          hidden_act: gelu
+          hidden_dropout_prob: 0.0
+          hidden_size: 1536
+          image_size: 518
+          initializer_range: 0.02
+          layer_norm_eps: 1.e-6
+          layerscale_value: 1.0
+          mlp_ratio: 4
+          model_type: dinov2
+          num_attention_heads: 24
+          num_channels: 3
+          num_hidden_layers: 40
+          patch_size: 14
+          qkv_bias: true
+          torch_dtype: float32
+          use_swiglu_ffn: true
+        image_size: 518
+
+scheduler:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.schedulers.FlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+
+image_processor:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.preprocessors.ImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,69 @@
+model:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.Hunyuan3DDiT
+  params:
+    in_channels: 64
+    context_in_dim: 1536
+    hidden_size: 1024
+    mlp_ratio: 4.0
+    num_heads: 16
+    depth: 16
+    depth_single_blocks: 32
+    axes_dim: [ 64 ]
+    theta: 10000
+    qkv_bias: true
+    guidance_embed: true
+
+vae:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+  params:
+    num_latents: 3072
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 0.9990943042622529
+
+conditioner:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.SingleImageEncoder
+  params:
+    main_image_encoder:
+      type: DinoImageEncoderMV # dino giant
+      kwargs:
+        config:
+          attention_probs_dropout_prob: 0.0
+          drop_path_rate: 0.0
+          hidden_act: gelu
+          hidden_dropout_prob: 0.0
+          hidden_size: 1536
+          image_size: 518
+          initializer_range: 0.02
+          layer_norm_eps: 1.e-6
+          layerscale_value: 1.0
+          mlp_ratio: 4
+          model_type: dinov2
+          num_attention_heads: 24
+          num_channels: 3
+          num_hidden_layers: 40
+          patch_size: 14
+          qkv_bias: true
+          torch_dtype: float32
+          use_swiglu_ffn: true
+        image_size: 518
+
+scheduler:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.schedulers.FlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+
+image_processor:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.preprocessors.MVImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,70 @@
+model:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.Hunyuan3DDiT
+  params:
+    in_channels: 64
+    context_in_dim: 1536
+    hidden_size: 1024
+    mlp_ratio: 4.0
+    num_heads: 16
+    depth: 16
+    depth_single_blocks: 32
+    axes_dim: [ 64 ]
+    theta: 10000
+    qkv_bias: true
+    guidance_embed: true
+
+vae:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+  params:
+    num_latents: 3072
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 0.9990943042622529
+
+conditioner:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.SingleImageEncoder
+  params:
+    main_image_encoder:
+      type: DinoImageEncoderMV # dino giant
+      kwargs:
+        config:
+          attention_probs_dropout_prob: 0.0
+          drop_path_rate: 0.0
+          hidden_act: gelu
+          hidden_dropout_prob: 0.0
+          hidden_size: 1536
+          image_size: 518
+          initializer_range: 0.02
+          layer_norm_eps: 1.e-6
+          layerscale_value: 1.0
+          mlp_ratio: 4
+          model_type: dinov2
+          num_attention_heads: 24
+          num_channels: 3
+          num_hidden_layers: 40
+          patch_size: 14
+          qkv_bias: true
+          torch_dtype: float32
+          use_swiglu_ffn: true
+        image_size: 518
+
+scheduler:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.schedulers.ConsistencyFlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+    pcm_timesteps: 100
+
+image_processor:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.preprocessors.MVImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,68 @@
+model:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.Hunyuan3DDiT
+  params:
+    in_channels: 64
+    context_in_dim: 1536
+    hidden_size: 1024
+    mlp_ratio: 4.0
+    num_heads: 16
+    depth: 16
+    depth_single_blocks: 32
+    axes_dim: [ 64 ]
+    theta: 10000
+    qkv_bias: true
+
+vae:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.ShapeVAE
+  params:
+    num_latents: 3072
+    embed_dim: 64
+    num_freqs: 8
+    include_pi: false
+    heads: 16
+    width: 1024
+    num_decoder_layers: 16
+    qkv_bias: false
+    qk_norm: true
+    scale_factor: 0.9990943042622529
+
+conditioner:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.models.SingleImageEncoder
+  params:
+    main_image_encoder:
+      type: DinoImageEncoderMV # dino giant
+      kwargs:
+        config:
+          attention_probs_dropout_prob: 0.0
+          drop_path_rate: 0.0
+          hidden_act: gelu
+          hidden_dropout_prob: 0.0
+          hidden_size: 1536
+          image_size: 518
+          initializer_range: 0.02
+          layer_norm_eps: 1.e-6
+          layerscale_value: 1.0
+          mlp_ratio: 4
+          model_type: dinov2
+          num_attention_heads: 24
+          num_channels: 3
+          num_hidden_layers: 40
+          patch_size: 14
+          qkv_bias: true
+          torch_dtype: float32
+          use_swiglu_ffn: true
+        image_size: 518
+
+scheduler:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.schedulers.FlowMatchEulerDiscreteScheduler
+  params:
+    num_train_timesteps: 1000
+
+image_processor:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.preprocessors.MVImageProcessorV2
+  params:
+    size: 512
+    border_ratio: 0.15
+
+pipeline:
+  target: Hunyuan3D_V2.hy3dgen.shapegen.pipelines.Hunyuan3DDiTFlowMatchingPipeline
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,18 @@
+---
+license: mit
+pipeline_tag: image-to-3d
+tags:
+- partcrafter
+- 3d-generation
+- rectified-flow
+---
+# PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers (Scene Level)
+
+PartCrafter is a structured 3D generative model that jointly generates multiple parts and objects from a single RGB image in one shot.
+This HuggingFace🤗 repo stores pretrained model weights for PartCrafter on **scene level**. 
+
+For more details about usage, please refer to the [official GitHub repo](https://github.com/wgsxm/PartCrafter).
+
+- Project page: https://wgsxm.github.io/projects/partcrafter/
+- Code: https://github.com/wgsxm/PartCrafter
+- Paper: https://arxiv.org/abs/2506.05573
@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}
@@ -0,0 +1,60 @@
+{
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2Model"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "out_features": [
+    "stage24"
+  ],
+  "out_indices": [
+    24
+  ],
+  "patch_size": 14,
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12",
+    "stage13",
+    "stage14",
+    "stage15",
+    "stage16",
+    "stage17",
+    "stage18",
+    "stage19",
+    "stage20",
+    "stage21",
+    "stage22",
+    "stage23",
+    "stage24"
+  ],
+  "torch_dtype": "float16",
+  "transformers_version": "4.53.2",
+  "use_mask_token": true,
+  "use_swiglu_ffn": false
+}
@@ -0,0 +1,24 @@
+{
+  "_class_name": "PartCrafterPipeline",
+  "_diffusers_version": "0.34.0",
+  "feature_extractor_dinov2": [
+    "transformers",
+    "BitImageProcessor"
+  ],
+  "image_encoder_dinov2": [
+    "transformers",
+    "Dinov2Model"
+  ],
+  "scheduler": [
+    "partcrafter_src.schedulers.scheduling_rectified_flow",
+    "RectifiedFlowScheduler"
+  ],
+  "transformer": [
+    "partcrafter_src.models.transformers.partcrafter_transformer",
+    "PartCrafterDiTModel"
+  ],
+  "vae": [
+    "partcrafter_src.models.autoencoders.autoencoder_kl_triposg",
+    "TripoSGVAEModel"
+  ]
+}
@@ -0,0 +1,7 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.34.0",
+  "num_train_timesteps": 1000,
+  "shift": 1,
+  "use_dynamic_shifting": false
+}
@@ -0,0 +1,27 @@
+{
+  "_class_name": "PartCrafterDiTModel",
+  "_diffusers_version": "0.34.0",
+  "cross_attention_dim": 1024,
+  "enable_global_cross_attn": true,
+  "enable_local_cross_attn": true,
+  "enable_part_embedding": true,
+  "global_attn_block_id_range": null,
+  "global_attn_block_ids": [
+    0,
+    2,
+    4,
+    6,
+    8,
+    10,
+    12,
+    14,
+    16,
+    18,
+    20
+  ],
+  "in_channels": 64,
+  "max_num_parts": 32,
+  "num_attention_heads": 16,
+  "num_layers": 21,
+  "width": 2048
+}
@@ -0,0 +1,15 @@
+{
+  "_class_name": "TripoSGVAEModel",
+  "_diffusers_version": "0.34.0",
+  "_name_or_path": "pretrained_weights/TripoSG",
+  "embed_frequency": 8,
+  "embed_include_pi": false,
+  "embedding_type": "frequency",
+  "in_channels": 3,
+  "latent_channels": 64,
+  "num_attention_heads": 8,
+  "num_layers_decoder": 16,
+  "num_layers_encoder": 8,
+  "width_decoder": 1024,
+  "width_encoder": 512
+}
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
@@ -0,0 +1,18 @@
+---
+license: mit
+pipeline_tag: image-to-3d
+tags:
+- partcrafter
+- 3d-generation
+- rectified-flow
+---
+# PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers
+
+PartCrafter is a structured 3D generative model that jointly generates multiple parts and objects from a single RGB image in one shot.
+This HuggingFace🤗 repo stores pretrained model weights for PartCrafter on **object level**. 
+
+For more details about usage, please refer to the [official GitHub repo](https://github.com/wgsxm/PartCrafter).
+
+- Project page: https://wgsxm.github.io/projects/partcrafter/
+- Code: https://github.com/wgsxm/PartCrafter
+- Paper: https://arxiv.org/abs/2506.05573
@@ -0,0 +1,27 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.485,
+    0.456,
+    0.406
+  ],
+  "image_processor_type": "BitImageProcessor",
+  "image_std": [
+    0.229,
+    0.224,
+    0.225
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 256
+  }
+}
@@ -0,0 +1,60 @@
+{
+  "apply_layernorm": true,
+  "architectures": [
+    "Dinov2Model"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "drop_path_rate": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1024,
+  "image_size": 518,
+  "initializer_range": 0.02,
+  "layer_norm_eps": 1e-06,
+  "layerscale_value": 1.0,
+  "mlp_ratio": 4,
+  "model_type": "dinov2",
+  "num_attention_heads": 16,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "out_features": [
+    "stage24"
+  ],
+  "out_indices": [
+    24
+  ],
+  "patch_size": 14,
+  "qkv_bias": true,
+  "reshape_hidden_states": true,
+  "stage_names": [
+    "stem",
+    "stage1",
+    "stage2",
+    "stage3",
+    "stage4",
+    "stage5",
+    "stage6",
+    "stage7",
+    "stage8",
+    "stage9",
+    "stage10",
+    "stage11",
+    "stage12",
+    "stage13",
+    "stage14",
+    "stage15",
+    "stage16",
+    "stage17",
+    "stage18",
+    "stage19",
+    "stage20",
+    "stage21",
+    "stage22",
+    "stage23",
+    "stage24"
+  ],
+  "torch_dtype": "float16",
+  "transformers_version": "4.53.0",
+  "use_mask_token": true,
+  "use_swiglu_ffn": false
+}
@@ -0,0 +1,24 @@
+{
+  "_class_name": "PartCrafterPipeline",
+  "_diffusers_version": "0.34.0",
+  "feature_extractor_dinov2": [
+    "transformers",
+    "BitImageProcessor"
+  ],
+  "image_encoder_dinov2": [
+    "transformers",
+    "Dinov2Model"
+  ],
+  "scheduler": [
+    "partcrafter_src.schedulers.scheduling_rectified_flow",
+    "RectifiedFlowScheduler"
+  ],
+  "transformer": [
+    "partcrafter_src.models.transformers.partcrafter_transformer",
+    "PartCrafterDiTModel"
+  ],
+  "vae": [
+    "partcrafter_src.models.autoencoders.autoencoder_kl_triposg",
+    "TripoSGVAEModel"
+  ]
+}
@@ -0,0 +1,7 @@
+{
+  "_class_name": "RectifiedFlowScheduler",
+  "_diffusers_version": "0.34.0",
+  "num_train_timesteps": 1000,
+  "shift": 1,
+  "use_dynamic_shifting": false
+}
@@ -0,0 +1,27 @@
+{
+  "_class_name": "PartCrafterDiTModel",
+  "_diffusers_version": "0.34.0",
+  "cross_attention_dim": 1024,
+  "enable_global_cross_attn": true,
+  "enable_local_cross_attn": true,
+  "enable_part_embedding": true,
+  "global_attn_block_id_range": null,
+  "global_attn_block_ids": [
+    0,
+    2,
+    4,
+    6,
+    8,
+    10,
+    12,
+    14,
+    16,
+    18,
+    20
+  ],
+  "in_channels": 64,
+  "max_num_parts": 32,
+  "num_attention_heads": 16,
+  "num_layers": 21,
+  "width": 2048
+}
@@ -0,0 +1,15 @@
+{
+  "_class_name": "TripoSGVAEModel",
+  "_diffusers_version": "0.34.0",
+  "_name_or_path": "pretrained_weights/TripoSG",
+  "embed_frequency": 8,
+  "embed_include_pi": false,
+  "embedding_type": "frequency",
+  "in_channels": 3,
+  "latent_channels": 64,
+  "num_attention_heads": 8,
+  "num_layers_decoder": 16,
+  "num_layers_encoder": 8,
+  "width_decoder": 1024,
+  "width_encoder": 512
+}
@@ -0,0 +1,123 @@
+name: ig2mv
+tag: "r768-ortho-nv6-ig2mv-partialimg-dcrowcol-sdxl"
+exp_root_dir: "outputs"
+seed: 42
+
+data_cls: mvadapter.data.multiview.MultiviewDataModule
+data:
+  root_dir: data/texture_ortho6view_easylight
+  scene_list: data/objaverse_list_6w.json
+  background_color: gray
+  image_names: ["0000", "0001", "0002", "0003", "0008", "0009"]
+  image_modality: color
+  num_views: 6
+
+  prompt_db_path: data/objaverse_short_captions.json
+  return_prompt: true
+
+  projection_type: ORTHO
+
+  source_image_modality: ["position", "normal"]
+  position_offset: 0.5
+  position_scale: 1.0
+
+  reference_root_dir: ["data/texture_rand_easylight_objaverse"]
+  reference_scene_list: ["data/objaverse_list_6w.json"]
+  reference_image_modality: color
+  reference_image_names: ["0000", "0001", "0002", "0003", "0004"]
+  reference_mask_aug: true
+
+  train_indices: [0, -8]
+  val_indices: [-8, null]
+  test_indices: [-8, null]
+
+  height: 768
+  width: 768
+
+  batch_size: 1
+  num_workers: 16
+
+system_cls: mvadapter.systems.mvadapter_image_sdxl.MVAdapterImageSDXLSystem
+system:
+  check_train_every_n_steps: 1000
+  cleanup_after_validation_step: true
+  cleanup_after_test_step: true
+
+  # Model / Adapter
+  pretrained_model_name_or_path: "stabilityai/stable-diffusion-xl-base-1.0"
+  pretrained_vae_name_or_path: "madebyollin/sdxl-vae-fp16-fix"
+  pretrained_adapter_name_or_path: null
+  init_adapter_kwargs:
+    # Multi-view adapter
+    self_attn_processor: "mvadapter.models.attention_processor.DecoupledMVRowColSelfAttnProcessor2_0"
+    # Condition encoder
+    cond_in_channels: 6
+    # For training
+    copy_attn_weights: true
+    zero_init_module_keys: ["to_out_mv", "to_out_ref"]
+
+  # Training
+  train_cond_encoder: true
+  trainable_modules: ["_mv", "_ref"]
+  prompt_drop_prob: 0.1
+  image_drop_prob: 0.1
+  cond_drop_prob: 0.1
+
+  # Noise sampler
+  shift_noise: true
+  shift_noise_mode: interpolated
+  shift_noise_scale: 8
+
+  # Evaluation
+  eval_seed: 42
+  eval_num_inference_steps: 30
+  eval_guidance_scale: 3.0
+  eval_height: ${data.height}
+  eval_width: ${data.width}
+
+  # optimizer definition
+  # you can set different learning rates separately for each group of parameters, but note that if you do this you should specify EVERY trainable parameters
+  optimizer:
+    name: AdamW
+    args:
+      lr: 5e-5
+      betas: [0.9, 0.999]
+      weight_decay: 0.01
+    params:
+      cond_encoder:
+        lr: 5e-5
+      unet:
+        lr: 5e-5
+
+  scheduler:
+    name: SequentialLR
+    interval: step
+    schedulers:
+      - name: LinearLR
+        interval: step
+        args:
+          start_factor: 1e-6
+          end_factor: 1.0
+          total_iters: 2000
+      - name: ConstantLR
+        interval: step
+        args:
+          factor: 1.0
+          total_iters: 9999999
+    milestones: [2000]
+
+trainer:
+  max_epochs: 10
+  log_every_n_steps: 10
+  num_sanity_val_steps: 1
+  val_check_interval: 2000
+  enable_progress_bar: true
+  precision: bf16-mixed
+  gradient_clip_val: 1.0
+  strategy: ddp
+  accumulate_grad_batches: 1
+
+checkpoint:
+  save_last: true # whether to save at each validation time
+  save_top_k: -1
+  every_n_epochs: 9999 # do not save at all for debug purpose
@@ -0,0 +1,122 @@
+name: ig2mv
+tag: "r768-ortho-nv6-ig2mv-dcrowcol-sdxl"
+exp_root_dir: "outputs"
+seed: 42
+
+data_cls: mvadapter.data.multiview.MultiviewDataModule
+data:
+  root_dir: data/texture_ortho6view_easylight
+  scene_list: data/objaverse_list_6w.json
+  background_color: gray
+  image_names: ["0000", "0001", "0002", "0003", "0008", "0009"]
+  image_modality: color
+  num_views: 6
+
+  prompt_db_path: data/objaverse_short_captions.json
+  return_prompt: true
+
+  projection_type: ORTHO
+
+  source_image_modality: ["position", "normal"]
+  position_offset: 0.5
+  position_scale: 1.0
+
+  reference_root_dir: ["data/texture_rand_easylight_objaverse"]
+  reference_scene_list: ["data/objaverse_list_6w.json"]
+  reference_image_modality: color
+  reference_image_names: ["0000", "0001", "0002", "0003", "0004"]
+
+  train_indices: [0, -8]
+  val_indices: [-8, null]
+  test_indices: [-8, null]
+
+  height: 768
+  width: 768
+
+  batch_size: 1
+  num_workers: 16
+
+system_cls: mvadapter.systems.mvadapter_image_sdxl.MVAdapterImageSDXLSystem
+system:
+  check_train_every_n_steps: 1000
+  cleanup_after_validation_step: true
+  cleanup_after_test_step: true
+
+  # Model / Adapter
+  pretrained_model_name_or_path: "stabilityai/stable-diffusion-xl-base-1.0"
+  pretrained_vae_name_or_path: "madebyollin/sdxl-vae-fp16-fix"
+  pretrained_adapter_name_or_path: null
+  init_adapter_kwargs:
+    # Multi-view adapter
+    self_attn_processor: "mvadapter.models.attention_processor.DecoupledMVRowColSelfAttnProcessor2_0"
+    # Condition encoder
+    cond_in_channels: 6
+    # For training
+    copy_attn_weights: true
+    zero_init_module_keys: ["to_out_mv", "to_out_ref"]
+
+  # Training
+  train_cond_encoder: true
+  trainable_modules: ["_mv", "_ref"]
+  prompt_drop_prob: 0.1
+  image_drop_prob: 0.1
+  cond_drop_prob: 0.1
+
+  # Noise sampler
+  shift_noise: true
+  shift_noise_mode: interpolated
+  shift_noise_scale: 8
+
+  # Evaluation
+  eval_seed: 42
+  eval_num_inference_steps: 30
+  eval_guidance_scale: 3.0
+  eval_height: ${data.height}
+  eval_width: ${data.width}
+
+  # optimizer definition
+  # you can set different learning rates separately for each group of parameters, but note that if you do this you should specify EVERY trainable parameters
+  optimizer:
+    name: AdamW
+    args:
+      lr: 5e-5
+      betas: [0.9, 0.999]
+      weight_decay: 0.01
+    params:
+      cond_encoder:
+        lr: 5e-5
+      unet:
+        lr: 5e-5
+
+  scheduler:
+    name: SequentialLR
+    interval: step
+    schedulers:
+      - name: LinearLR
+        interval: step
+        args:
+          start_factor: 1e-6
+          end_factor: 1.0
+          total_iters: 2000
+      - name: ConstantLR
+        interval: step
+        args:
+          factor: 1.0
+          total_iters: 9999999
+    milestones: [2000]
+
+trainer:
+  max_epochs: 10
+  log_every_n_steps: 10
+  num_sanity_val_steps: 1
+  val_check_interval: 2000
+  enable_progress_bar: true
+  precision: bf16-mixed
+  gradient_clip_val: 1.0
+  strategy: ddp
+  accumulate_grad_batches: 1
+
+checkpoint:
+  save_last: true # whether to save at each validation time
+  save_top_k: -1
+  every_n_epochs: 9999 # do not save at all for debug purpose
@@ -0,0 +1,117 @@
+name: tg2mv
+tag: "r768-ortho-nv6-tg2mv-dcrowcol-sdxl"
+exp_root_dir: "outputs"
+seed: 42
+
+data_cls: mvadapter.data.multiview.MultiviewDataModule
+data:
+  root_dir: data/texture_ortho10view_easylight_objaverse
+  scene_list: data/objaverse_list_6w.json
+  background_color: gray
+  image_names: ["0000", "0001", "0002", "0003", "0008", "0009"]
+  image_modality: color
+  num_views: 6
+
+  prompt_db_path: data/objaverse_short_captions.json
+  return_prompt: true
+
+  projection_type: ORTHO
+
+  source_image_modality: ["position", "normal"]
+  position_offset: 0.5
+  position_scale: 1.0
+
+  train_indices: [0, -8]
+  val_indices: [-8, null]
+  test_indices: [-8, null]
+
+  height: 768
+  width: 768
+
+  batch_size: 1
+  num_workers: 16
+
+system_cls: mvadapter.systems.mvadapter_text_sdxl.MVAdapterTextSDXLSystem
+system:
+  check_train_every_n_steps: 1000
+  cleanup_after_validation_step: true
+  cleanup_after_test_step: true
+
+  # Model / Adapter
+  pretrained_model_name_or_path: "stabilityai/stable-diffusion-xl-base-1.0"
+  pretrained_vae_name_or_path: "madebyollin/sdxl-vae-fp16-fix"
+  pretrained_adapter_name_or_path: null
+  init_adapter_kwargs:
+    # Multi-view adapter
+    self_attn_processor: "mvadapter.models.attention_processor.DecoupledMVRowColSelfAttnProcessor2_0"
+    # Condition encoder
+    cond_in_channels: 6
+    # For training
+    copy_attn_weights: true
+    zero_init_module_keys: ["to_out_mv"]
+
+  # Training
+  train_cond_encoder: true
+  trainable_modules: ["_mv"]
+  prompt_drop_prob: 0.1
+  image_drop_prob: 0.1
+  cond_drop_prob: 0.1
+
+  # Noise sampler
+  shift_noise: true
+  shift_noise_mode: interpolated
+  shift_noise_scale: 8
+
+  # Evaluation
+  eval_seed: 42
+  eval_num_inference_steps: 30
+  eval_guidance_scale: 3.0
+  eval_height: ${data.height}
+  eval_width: ${data.width}
+
+  # optimizer definition
+  # you can set different learning rates separately for each group of parameters, but note that if you do this you should specify EVERY trainable parameters
+  optimizer:
+    name: AdamW
+    args:
+      lr: 5e-5
+      betas: [0.9, 0.999]
+      weight_decay: 0.01
+    params:
+      cond_encoder:
+        lr: 5e-5
+      unet:
+        lr: 5e-5
+
+  scheduler:
+    name: SequentialLR
+    interval: step
+    schedulers:
+      - name: LinearLR
+        interval: step
+        args:
+          start_factor: 1e-6
+          end_factor: 1.0
+          total_iters: 2000
+      - name: ConstantLR
+        interval: step
+        args:
+          factor: 1.0
+          total_iters: 9999999
+    milestones: [2000]
+
+trainer:
+  max_epochs: 10
+  log_every_n_steps: 10
+  num_sanity_val_steps: 1
+  val_check_interval: 2000
+  enable_progress_bar: true
+  precision: bf16-mixed
+  gradient_clip_val: 1.0
+  strategy: ddp
+  accumulate_grad_batches: 1
+
+checkpoint:
+  save_last: true # whether to save at each validation time
+  save_top_k: -1
+  every_n_epochs: 9999 # do not save at all for debug purpose
@@ -0,0 +1,122 @@
+name: i2mv
+tag: "r512-ortho-nv6-ele0-sd21"
+exp_root_dir: "outputs"
+seed: 42
+
+data_cls: mvadapter.data.multiview.MultiviewDataModule
+data:
+  root_dir: "data/texture_ortho10view_easylight_objaverse"
+  scene_list: "data/objaverse_list_6w.json"
+  background_color: gray
+  image_names: ["0000", "0004", "0001", "0002", "0003", "0005"]
+  image_modality: color
+  num_views: 6
+
+  prompt_db_path: data/objaverse_short_captions.json
+  return_prompt: true
+
+  projection_type: ORTHO
+
+  source_image_modality: ["plucker"]
+  plucker_offset: 1.0
+  plucker_scale: 2.0
+
+  reference_root_dir: ["data/texture_rand_easylight_objaverse"]
+  reference_scene_list: ["data/objaverse_list_6w.json"]
+  reference_image_modality: color
+  reference_image_names: ["0000", "0001", "0002", "0003", "0004"]
+
+  train_indices: [0, -8]
+  val_indices: [-8, null]
+  test_indices: [-8, null]
+
+  height: 512
+  width: 512
+
+  batch_size: 1
+  num_workers: 16
+
+system_cls: mvadapter.systems.mvadapter_image_sd.MVAdapterImageSDSystem
+system:
+  check_train_every_n_steps: 1000
+  cleanup_after_validation_step: true
+  cleanup_after_test_step: true
+
+  # Model / Adapter
+  pretrained_model_name_or_path: "stabilityai/stable-diffusion-2-1-base"
+  pretrained_vae_name_or_path: null
+  pretrained_adapter_name_or_path: null
+  init_adapter_kwargs:
+    # Multi-view adapter
+    self_attn_processor: "mvadapter.models.attention_processor.DecoupledMVRowSelfAttnProcessor2_0"
+    # Condition encoder
+    cond_in_channels: 6
+    # For training
+    copy_attn_weights: true
+    zero_init_module_keys: ["to_out_mv", "to_out_ref"]
+
+  # Training
+  train_cond_encoder: true
+  trainable_modules: ["_mv", "_ref"]
+  prompt_drop_prob: 0.1
+  image_drop_prob: 0.1
+  cond_drop_prob: 0.1
+
+  # Noise sampler
+  shift_noise: true
+  shift_noise_mode: interpolated
+  shift_noise_scale: 8
+
+  # Evaluation
+  eval_seed: 42
+  eval_num_inference_steps: 30
+  eval_guidance_scale: 3.0
+  eval_height: ${data.height}
+  eval_width: ${data.width}
+
+  # optimizer definition
+  # you can set different learning rates separately for each group of parameters, but note that if you do this you should specify EVERY trainable parameters
+  optimizer:
+    name: AdamW
+    args:
+      lr: 5e-5
+      betas: [0.9, 0.999]
+      weight_decay: 0.01
+    params:
+      cond_encoder:
+        lr: 5e-5
+      unet:
+        lr: 5e-5
+
+  scheduler:
+    name: SequentialLR
+    interval: step
+    schedulers:
+      - name: LinearLR
+        interval: step
+        args:
+          start_factor: 1e-6
+          end_factor: 1.0
+          total_iters: 2000
+      - name: ConstantLR
+        interval: step
+        args:
+          factor: 1.0
+          total_iters: 9999999
+    milestones: [2000]
+
+trainer:
+  max_epochs: 5
+  log_every_n_steps: 10
+  num_sanity_val_steps: 1
+  val_check_interval: 2000
+  enable_progress_bar: true
+  precision: bf16-mixed
+  gradient_clip_val: 1.0
+  strategy: ddp
+  accumulate_grad_batches: 1
+
+checkpoint:
+  save_last: true # whether to save at each validation time
+  save_top_k: -1
+  every_n_epochs: 9999 # do not save at all for debug purpose
@@ -0,0 +1,122 @@
+name: i2mv
+tag: "r768-ortho-nv6-ele0-sdxl"
+exp_root_dir: "outputs"
+seed: 42
+
+data_cls: mvadapter.data.multiview.MultiviewDataModule
+data:
+  root_dir: "data/texture_ortho10view_easylight_objaverse"
+  scene_list: "data/objaverse_list_6w.json"
+  background_color: gray
+  image_names: ["0000", "0004", "0001", "0002", "0003", "0005"]
+  image_modality: color
+  num_views: 6
+
+  prompt_db_path: data/objaverse_short_captions.json
+  return_prompt: true
+
+  projection_type: ORTHO
+
+  source_image_modality: ["plucker"]
+  plucker_offset: 1.0
+  plucker_scale: 2.0
+
+  reference_root_dir: ["data/texture_rand_easylight_objaverse"]
+  reference_scene_list: ["data/objaverse_list_6w.json"]
+  reference_image_modality: color
+  reference_image_names: ["0000", "0001", "0002", "0003", "0004"]
+
+  train_indices: [0, -8]
+  val_indices: [-8, null]
+  test_indices: [-8, null]
+
+  height: 768
+  width: 768
+
+  batch_size: 1
+  num_workers: 16
+
+system_cls: mvadapter.systems.mvadapter_image_sdxl.MVAdapterImageSDXLSystem
+system:
+  check_train_every_n_steps: 1000
+  cleanup_after_validation_step: true
+  cleanup_after_test_step: true
+
+  # Model / Adapter
+  pretrained_model_name_or_path: "stabilityai/stable-diffusion-xl-base-1.0"
+  pretrained_vae_name_or_path: "madebyollin/sdxl-vae-fp16-fix"
+  pretrained_adapter_name_or_path: null
+  init_adapter_kwargs:
+    # Multi-view adapter
+    self_attn_processor: "mvadapter.models.attention_processor.DecoupledMVRowSelfAttnProcessor2_0"
+    # Condition encoder
+    cond_in_channels: 6
+    # For training
+    copy_attn_weights: true
+    zero_init_module_keys: ["to_out_mv", "to_out_ref"]
+
+  # Training
+  train_cond_encoder: true
+  trainable_modules: ["_mv", "_ref"]
+  prompt_drop_prob: 0.1
+  image_drop_prob: 0.1
+  cond_drop_prob: 0.1
+
+  # Noise sampler
+  shift_noise: true
+  shift_noise_mode: interpolated
+  shift_noise_scale: 8
+
+  # Evaluation
+  eval_seed: 42
+  eval_num_inference_steps: 30
+  eval_guidance_scale: 3.0
+  eval_height: ${data.height}
+  eval_width: ${data.width}
+
+  # optimizer definition
+  # you can set different learning rates separately for each group of parameters, but note that if you do this you should specify EVERY trainable parameters
+  optimizer:
+    name: AdamW
+    args:
+      lr: 5e-5
+      betas: [0.9, 0.999]
+      weight_decay: 0.01
+    params:
+      cond_encoder:
+        lr: 5e-5
+      unet:
+        lr: 5e-5
+
+  scheduler:
+    name: SequentialLR
+    interval: step
+    schedulers:
+      - name: LinearLR
+        interval: step
+        args:
+          start_factor: 1e-6
+          end_factor: 1.0
+          total_iters: 2000
+      - name: ConstantLR
+        interval: step
+        args:
+          factor: 1.0
+          total_iters: 9999999
+    milestones: [2000]
+
+trainer:
+  max_epochs: 10
+  log_every_n_steps: 10
+  num_sanity_val_steps: 1
+  val_check_interval: 2000
+  enable_progress_bar: true
+  precision: bf16-mixed
+  gradient_clip_val: 1.0
+  strategy: ddp
+  accumulate_grad_batches: 1
+
+checkpoint:
+  save_last: true # whether to save at each validation time
+  save_top_k: -1
+  every_n_epochs: 9999 # do not save at all for debug purpose
@@ -0,0 +1,123 @@
+name: i2mv
+tag: "r768-ortho-nv6-ele0-sdxl-aug-quantity"
+exp_root_dir: "outputs"
+seed: 42
+
+data_cls: mvadapter.data.multiview.MultiviewDataModule
+data:
+  root_dir: "data/texture_ortho10view_easylight_objaverse"
+  scene_list: "data/objaverse_list_6w.json"
+  background_color: gray
+  image_names: ["0000", "0004", "0001", "0002", "0003", "0005"]
+  image_modality: color
+  num_views: 6
+  random_view_list: [[0, 1, 2, 3, 4, 5], [0, 2, 3, 4], [0, 2, 3], [0, 3]]
+
+  prompt_db_path: data/objaverse_short_captions.json
+  return_prompt: true
+
+  projection_type: ORTHO
+
+  source_image_modality: ["plucker"]
+  plucker_offset: 1.0
+  plucker_scale: 2.0
+
+  reference_root_dir: ["data/texture_rand_easylight_objaverse"]
+  reference_scene_list: ["data/objaverse_list_6w.json"]
+  reference_image_modality: color
+  reference_image_names: ["0000", "0001", "0002", "0003", "0004"]
+
+  train_indices: [0, -8]
+  val_indices: [-8, null]
+  test_indices: [-8, null]
+
+  height: 768
+  width: 768
+
+  batch_size: 1
+  num_workers: 16
+
+system_cls: mvadapter.systems.mvadapter_image_sdxl.MVAdapterImageSDXLSystem
+system:
+  check_train_every_n_steps: 1000
+  cleanup_after_validation_step: true
+  cleanup_after_test_step: true
+
+  # Model / Adapter
+  pretrained_model_name_or_path: "stabilityai/stable-diffusion-xl-base-1.0"
+  pretrained_vae_name_or_path: "madebyollin/sdxl-vae-fp16-fix"
+  pretrained_adapter_name_or_path: null
+  init_adapter_kwargs:
+    # Multi-view adapter
+    self_attn_processor: "mvadapter.models.attention_processor.DecoupledMVRowSelfAttnProcessor2_0"
+    # Condition encoder
+    cond_in_channels: 6
+    # For training
+    copy_attn_weights: true
+    zero_init_module_keys: ["to_out_mv", "to_out_ref"]
+
+  # Training
+  train_cond_encoder: true
+  trainable_modules: ["_mv", "_ref"]
+  prompt_drop_prob: 0.1
+  image_drop_prob: 0.1
+  cond_drop_prob: 0.1
+
+  # Noise sampler
+  shift_noise: true
+  shift_noise_mode: interpolated
+  shift_noise_scale: 8
+
+  # Evaluation
+  eval_seed: 42
+  eval_num_inference_steps: 30
+  eval_guidance_scale: 3.0
+  eval_height: ${data.height}
+  eval_width: ${data.width}
+
+  # optimizer definition
+  # you can set different learning rates separately for each group of parameters, but note that if you do this you should specify EVERY trainable parameters
+  optimizer:
+    name: AdamW
+    args:
+      lr: 5e-5
+      betas: [0.9, 0.999]
+      weight_decay: 0.01
+    params:
+      cond_encoder:
+        lr: 5e-5
+      unet:
+        lr: 5e-5
+
+  scheduler:
+    name: SequentialLR
+    interval: step
+    schedulers:
+      - name: LinearLR
+        interval: step
+        args:
+          start_factor: 1e-6
+          end_factor: 1.0
+          total_iters: 2000
+      - name: ConstantLR
+        interval: step
+        args:
+          factor: 1.0
+          total_iters: 9999999
+    milestones: [2000]
+
+trainer:
+  max_epochs: 10
+  log_every_n_steps: 10
+  num_sanity_val_steps: 1
+  val_check_interval: 2000
+  enable_progress_bar: true
+  precision: bf16-mixed
+  gradient_clip_val: 1.0
+  strategy: ddp
+  accumulate_grad_batches: 1
+
+checkpoint:
+  save_last: true # whether to save at each validation time
+  save_top_k: -1
+  every_n_epochs: 9999 # do not save at all for debug purpose
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
DenisKochetov	9e8096e50c	Merge pull request #545 from DenisKochetov/feature/update-unet-models Update UNet models for CharacterGen, Era3D, and Wonder3D	2025-11-17 22:25:56 +06:00
DenisKochetov	33ef3ee60c	Update UNet models for CharacterGen, Era3D, and Wonder3D	2025-11-12 09:27:17 +00:00
Mr. For Example	9ab02eb440	Merge pull request #522 from MrForExample/dev Merge from dev to main - Hunyuan3D 2.1 - PartCrafter with scene generation support	2025-08-07 18:44:26 +08:00
Mr. For Example	b4304038f8	Merge pull request #521 from DenisKochetov/example-workflows renamed example workflows to comfy-manager style	2025-08-07 18:32:52 +08:00
Denis Kochetov	9e37fa0420	renamed example workflows to comfy-manager style	2025-08-07 09:48:51 +00:00
Mr. For Example	5046f912d3	Merge pull request #520 from DenisKochetov/diffusers-fix updated code for diffusers fix charactergen	2025-08-07 17:01:44 +08:00
Denis Kochetov	51189f74ff	updated code for diffusers fix charactergen	2025-08-07 08:49:13 +00:00
Mr. For Example	68595bd7e8	Merge pull request #519 from DenisKochetov/partcrafter-rembg add white background	2025-08-07 12:22:20 +08:00
DenisKochetov	ca83e19986	add white background	2025-08-07 04:09:49 +00:00
Mr. For Example	cf913d2f1e	Merge pull request #518 from DenisKochetov/dev remove pyrender code	2025-08-01 10:24:20 +04:00
Denis Kochetov	39353a3637	remove pyrender code	2025-07-30 10:25:17 +00:00
Mr. For Example	14c4d3b887	Merge pull request #517 from DenisKochetov/partcrafter-scene Add partcrafter scene	2025-07-30 09:19:44 +04:00
Denis Kochetov	4785b7dd41	add test image	2025-07-29 18:49:38 +00:00
DenisKochetov	30f509c314	add demo video	2025-07-29 23:48:19 +05:00
Denis Kochetov	389ad56120	add example workflows	2025-07-29 18:39:19 +00:00
Denis Kochetov	06930669e2	add partcrafter scene	2025-07-29 18:34:02 +00:00
Mr. For Example	ffa5ff828e	Merge pull request #515 from DenisKochetov/partcrafter-fix Partcrafter fix	2025-07-26 09:52:22 +04:00
DenisKochetov	080747c5da	add demo video partcrafter	2025-07-25 23:43:23 +04:00
Denis Kochetov	13dc7b3d3d	fixed output mesh	2025-07-25 19:35:22 +00:00
Mr. For Example	6fa0039ad5	Merge pull request #513 from DenisKochetov/trellis-fix-torch fix trellis for updated torch	2025-07-24 18:23:24 +04:00
Mr. For Example	a1dab7a9a0	Merge pull request #514 from DenisKochetov/partcrafter add partcrafter	2025-07-24 18:23:11 +04:00
Denis Kochetov	8bf273ef47	add partcrafter	2025-07-24 13:51:07 +00:00
Denis Kochetov	f6f262df31	fix trellis for updated torch	2025-07-24 11:38:58 +00:00
Mr. For Example	7f8a85ab73	Merge branch 'main' into dev	2025-07-23 14:34:28 +04:00
Mr. For Example	bffeb83154	Merge pull request #507 from robinjhuang/patch-1 Bump to v0.1.6	2025-07-23 11:33:08 +01:00
Mr. For Example	5e1c29b723	Merge pull request #510 from DenisKochetov/rmbg-fix fixed rmbg for hunyuan and installation process	2025-07-23 11:32:41 +01:00
Denis Kochetov	2950530ae6	fix diso, spconv and mesh_painter installation	2025-07-17 22:10:59 +00:00
Denis Kochetov	78690f681e	fix rmbg for hunyuan	2025-07-17 18:53:42 +00:00
Robin Huang	7c7ac2429f	Bump to v0.1.6	2025-07-02 17:15:17 -07:00
DenisKochetov	aedee80e37	Merge branch 'MrForExample:dev' into dev	2025-06-25 21:05:37 +03:00
Mr. For Example	50f293d841	Merge pull request #500 from emmanuel-ferdman/main Update `README.md` reference in docker guide	2025-06-19 12:10:43 +01:00
Mr. For Example	c12fd93edc	Merge pull request #501 from DenisKochetov/hun-2.1 add hunyuan 2.1	2025-06-19 12:10:11 +01:00
DenisKochetov	e74cc4c083	updated demo videos	2025-06-19 01:36:57 +03:00
DenisKochetov	a303b1d8d1	Merge pull request #7 from DenisKochetov/hun-2.1 add hunyuan 2.1	2025-06-19 01:03:04 +03:00
DenisKochetov	c76b1a25b7	add hunyuan 2.1	2025-06-19 00:57:35 +03:00
Emmanuel Ferdman	7b8b1afbd6	Update `README.md` reference in docker guide Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>	2025-06-18 02:24:15 -07:00
Mr. For Example	4e33b6736d	Merge pull request #499 from huixingyun/fix-20250617 Fix: TypeError: Hunyuan3DPaintPipeline.from_pretrained() got an unexpected keyword argument 'torch_dtype'	2025-06-17 10:26:29 +01:00
Mr. For Example	693c7212f6	Merge pull request #497 from DenisKochetov/install-fix updated requirements	2025-06-17 10:26:10 +01:00
sko00o	4ab443c552	fix: TypeError: Hunyuan3DPaintPipeline.from_pretrained() got an unexpected keyword argument 'torch_dtype'	2025-06-17 11:35:43 +08:00
DenisKochetov	01aa751e79	updated requirements	2025-06-17 02:30:06 +03:00
Mr. For Example	fe2c9ce5bc	Merge pull request #494 from DenisKochetov/linux-install updated wheels installation	2025-06-15 15:13:42 +01:00
Ubuntu	b284bf9eb2	fix spconv cuda parsing	2025-06-13 09:29:45 +00:00
Ubuntu	464f475855	updated wheels installation	2025-06-13 08:03:21 +00:00
Mr. For Example	faa925cd16	Merge pull request #493 from MrForExample/dev Dev	2025-06-11 18:09:58 +01:00
Mr. For Example	9cb998eadd	Update install config	2025-06-11 18:08:10 +01:00
Mr. For Example	395a0071d7	Merge pull request #492 from DenisKochetov/installation-update updated installation to cuda 12.8	2025-06-11 14:28:19 +01:00
Denis Kochetov	4840690039	updated installation to cuda 12.8	2025-06-11 01:49:31 +03:00
Mr. For Example	9e68ae5eeb	Merge pull request #491 from DenisKochetov/mv-adapter-fix fix scheduler for mv-adapter	2025-06-07 12:59:39 +01:00
DenisKochetov	47f136ec19	update demo videos	2025-06-07 02:26:22 +03:00
Denis Kochetov	cd75086215	fix scheduler for mv-adapter	2025-06-06 23:21:30 +00:00
Mr. For Example	1f6bd293b6	Test Stable3DGen & minor UI change	2025-06-05 18:14:59 +01:00
Mr. For Example	b5670341b9	Merge pull request #489 from DenisKochetov/dev fix stablegen models downloading	2025-06-05 17:17:14 +01:00
DenisKochetov	a7df117d79	Merge branch 'MrForExample:dev' into dev	2025-06-05 19:04:11 +03:00
DenisKochetov	173ab54dbe	fix trellis model downloading	2025-06-05 18:39:35 +03:00
DenisKochetov	36a46d5e13	stablex model download fix	2025-06-05 18:21:23 +03:00
Mr. For Example	359e3b0e07	Fix potential triton mission issue	2025-06-05 13:47:53 +01:00
Mr. For Example	30b7c8cdb2	Merge branch 'main' into dev	2025-06-05 13:10:07 +01:00
Mr. For Example	a7fc5f19e0	Update nodes.py	2025-06-05 13:09:47 +01:00
Mr. For Example	1faae04a67	Merge pull request #485 from DenisKochetov/mv-adapter-start add mv-adapter ig2mv and t2v	2025-06-05 13:05:39 +01:00
DenisKochetov	55519ed726	updated demo videos and workflows links	2025-06-04 23:26:16 +03:00
Denis Kochetov	97975488c6	add mv-adapter texturing	2025-06-04 20:16:55 +00:00
Mr. For Example	00f42c7b57	Merge pull request #483 from DenisKochetov/dev add stable3dgen	2025-06-03 14:41:34 +01:00
Denis Kochetov	56640bc297	removed unnecessary files from dinov2	2025-06-02 22:11:52 +00:00
DenisKochetov	bd21742093	update demo videos	2025-06-03 00:58:00 +03:00
Denis Kochetov	626a5ee60d	remove unnecessary scripts and update output to multiple images	2025-06-02 21:07:17 +00:00
Mr. For Example	b3860b88c9	Merge pull request #459 from ComfyNodePRs/update-publish-yaml Update Github Action for Publishing to Comfy Registry	2025-05-31 14:17:56 +01:00
Mr. For Example	bbaefc44c4	Merge pull request #449 from sqlpxc/main fix wsl2 eglInitialize() failed	2025-05-31 14:15:33 +01:00
Mr. For Example	0ef55c5d1d	Merge pull request #447 from robinjhuang/rh-nodeid Change node id name.	2025-05-31 14:14:40 +01:00
DenisKochetov	5311a5f0d5	add demo videos	2025-05-30 11:48:48 +04:00
Denis Kochetov	76bb038e54	add mv-adapter to readme	2025-05-30 07:40:30 +00:00
Denis Kochetov	953b4919f7	add t2mv	2025-05-30 07:38:39 +00:00
Denis Kochetov	76179ca7fe	add mv-adapter ig2mv	2025-05-30 07:38:39 +00:00
DenisKochetov	ea90580926	add demo video for stable3dgen	2025-05-28 03:17:49 +04:00
Denis Kochetov	829fc82eee	add stable3dgen links to readme	2025-05-27 23:12:08 +00:00
Denis Kochetov	a1ce74e056	add dino to repo and custom downloading	2025-05-27 22:54:17 +00:00
Denis Kochetov	df3125c2b5	add stable3dgen	2025-05-27 20:46:38 +00:00
Mr. For Example	5a6f11c6a0	Merge branch 'main' into dev	2025-05-26 11:18:03 +01:00
Mr. For Example	10c87ed607	Merge branch 'main' into dev	2025-05-26 11:15:43 +01:00
Mr. For Example	4f68b0191b	Merge pull request #481 from DenisKochetov/main Fix broken model path for TRELLIS weights	2025-05-26 11:14:51 +01:00
DenisKochetov	d01ddb761c	renamed trellis checkpoints folder	2025-05-21 17:10:21 +04:00
DenisKochetov	d20c2b3aae	fix: fixed paths to trellis weights	2025-05-21 12:59:21 +04:00
Mr. For Example	e4fb7e55fd	Merge pull request #475 from DenisKochetov/dev Add Hunyuan V2 Turbo, Mini, Fast, MultiView	2025-05-10 10:12:56 -06:00
DenisKochetov	5c09246840	changed link to workflows	2025-05-10 04:05:10 +04:00
DenisKochetov	7a54db67b1	add workflows to readme	2025-05-10 03:36:07 +04:00
Denis Kochetov	b24ece2346	removed old workflows	2025-05-09 23:30:02 +00:00
Denis Kochetov	4066a81d43	add separate workflows and input images	2025-05-09 20:03:43 +00:00
Denis Kochetov	2ee2bbcedc	updated workflow	2025-05-08 02:38:23 +00:00
DenisKochetov	45bf0fd716	updated demo video	2025-05-08 06:37:03 +04:00
Denis Kochetov	ffc873a1d7	fix texturing multi view	2025-05-08 02:22:23 +00:00
Denis Kochetov	feaa3e03b1	add multiview	2025-05-08 02:22:13 +00:00
DenisKochetov	b0951721dc	remove commented code	2025-05-07 21:00:00 +04:00
DenisKochetov	1b523d0831	add demo video	2025-05-07 20:59:34 +04:00
Denis Kochetov	8aeeeecae5	feat: add Hunyuan3D-V2 Turbo, Fast, Mini models (MV not implemented yet)	2025-05-07 16:57:08 +00:00
Mr. For Example	2c62952240	Update README.md	2025-04-29 16:55:38 -06:00
Mr. For Example	a29213fecc	Update README.md	2025-04-29 16:53:46 -06:00
Mr. For Example	0768ba7a75	Integrated TripoSG plus Scribble model	2025-04-29 16:50:36 -06:00
sqlpxc	a9d45620c6	fix wsl2 eglInitialize() failed	2025-02-13 23:48:10 +08:00
Robin Huang	578ae2cbbc	Change node id name.	2025-02-04 14:40:31 -08:00
snomiao	247c9bb6d4	chore(publish): update GitHub Actions workflow for node publishing - Add permissions for writing issues - Restrict job execution to specific repository owner - Update action version to v1 for node publishing	2025-01-20 22:53:57 +00:00