add stable3dgen
This commit is contained in:
Denis Kochetov
@@ -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
|
||||
}
|
||||
+250
@@ -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"
|
||||
]
|
||||
}
|
||||
+17
@@ -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
|
||||
}
|
||||
}
|
||||
}
|
||||
+19
@@ -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
|
||||
}
|
||||
}
|
||||
+12
@@ -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
|
||||
}
|
||||
}
|
||||
+17
@@ -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"
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user