Fix Checkpoints folder name
This commit is contained in:
Mr. For Example
@@ -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 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c63c3d2e7b7f18788aca8a5a0e766ad4633f631d49192602d8532b6b0df7615
|
||||
size 559
|
||||
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "./image_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": "4.28.0.dev0"
|
||||
}
|
||||
@@ -0,0 +1,60 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- dino
|
||||
- vision
|
||||
---
|
||||
|
||||
# Vision Transformer (base-sized model) trained using DINOv2
|
||||
|
||||
Vision Transformer (ViT) model trained using the DINOv2 method. It was introduced in the paper [DINOv2: Learning Robust Visual Features without Supervision](https://arxiv.org/abs/2304.07193) by Oquab et al. and first released in [this repository](https://github.com/facebookresearch/dinov2).
|
||||
|
||||
Disclaimer: The team releasing DINOv2 did not write a model card for this model so this model card has been written by the Hugging Face team.
|
||||
|
||||
## Model description
|
||||
|
||||
The Vision Transformer (ViT) is a transformer encoder model (BERT-like) pretrained on a large collection of images in a self-supervised fashion.
|
||||
|
||||
Images are presented to the model as a sequence of fixed-size patches, which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.
|
||||
|
||||
Note that this model does not include any fine-tuned heads.
|
||||
|
||||
By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image.
|
||||
|
||||
## Intended uses & limitations
|
||||
|
||||
You can use the raw model for feature extraction. See the [model hub](https://huggingface.co/models?search=facebook/dinov2) to look for
|
||||
fine-tuned versions on a task that interests you.
|
||||
|
||||
### How to use
|
||||
|
||||
Here is how to use this model:
|
||||
|
||||
```python
|
||||
from transformers import AutoImageProcessor, AutoModel
|
||||
from PIL import Image
|
||||
import requests
|
||||
|
||||
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
|
||||
image = Image.open(requests.get(url, stream=True).raw)
|
||||
|
||||
processor = AutoImageProcessor.from_pretrained('facebook/dinov2-base')
|
||||
model = AutoModel.from_pretrained('facebook/dinov2-base')
|
||||
|
||||
inputs = processor(images=image, return_tensors="pt")
|
||||
outputs = model(**inputs)
|
||||
last_hidden_states = outputs.last_hidden_state
|
||||
```
|
||||
|
||||
### BibTeX entry and citation info
|
||||
|
||||
```bibtex
|
||||
misc{oquab2023dinov2,
|
||||
title={DINOv2: Learning Robust Visual Features without Supervision},
|
||||
author={Maxime Oquab and Timothée Darcet and Théo Moutakanni and Huy Vo and Marc Szafraniec and Vasil Khalidov and Pierre Fernandez and Daniel Haziza and Francisco Massa and Alaaeldin El-Nouby and Mahmoud Assran and Nicolas Ballas and Wojciech Galuba and Russell Howes and Po-Yao Huang and Shang-Wen Li and Ishan Misra and Michael Rabbat and Vasu Sharma and Gabriel Synnaeve and Hu Xu and Hervé Jegou and Julien Mairal and Patrick Labatut and Armand Joulin and Piotr Bojanowski},
|
||||
year={2023},
|
||||
eprint={2304.07193},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CV}
|
||||
}
|
||||
```
|
||||
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Dinov2Model"
|
||||
],
|
||||
"attention_probs_dropout_prob": 0.0,
|
||||
"drop_path_rate": 0.0,
|
||||
"hidden_act": "gelu",
|
||||
"hidden_dropout_prob": 0.0,
|
||||
"hidden_size": 768,
|
||||
"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": 12,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 12,
|
||||
"patch_size": 14,
|
||||
"qkv_bias": true,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.31.0.dev0",
|
||||
"use_swiglu_ffn": false
|
||||
}
|
||||
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"crop_size": {
|
||||
"height": 256,
|
||||
"width": 256
|
||||
},
|
||||
"do_center_crop": false,
|
||||
"do_convert_rgb": false,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": false,
|
||||
"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 +1,22 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: image-to-3d
|
||||
---
|
||||
|
||||
This is the model parameters of [CharacterGen](https://github.com/zjp-shadow/CharacterGen).
|
||||
Thanks for downloading the checkpoint~
|
||||
If you find our work helpful, please consider citing
|
||||
|
||||
```bibtex
|
||||
@article
|
||||
{peng2024charactergen,
|
||||
title ={CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization},
|
||||
author ={Hao-Yang Peng and Jia-Peng Zhang and Meng-Hao Guo and Yan-Pei Cao and Shi-Min Hu},
|
||||
journal ={ACM Transactions on Graphics (TOG)},
|
||||
year ={2024},
|
||||
volume ={43},
|
||||
number ={4},
|
||||
doi ={10.1145/3658217}
|
||||
}
|
||||
@@ -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 +1,5 @@
|
||||
---
|
||||
license: mit
|
||||
---
|
||||
To enable download model using huggingface_hub package
|
||||
<br>Copied from https://huggingface.co/spaces/Wuvin/Unique3D/tree/main/ckpt
|
||||
+44
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"_valid_processor_keys": [
|
||||
"images",
|
||||
"do_resize",
|
||||
"size",
|
||||
"resample",
|
||||
"do_center_crop",
|
||||
"crop_size",
|
||||
"do_rescale",
|
||||
"rescale_factor",
|
||||
"do_normalize",
|
||||
"image_mean",
|
||||
"image_std",
|
||||
"do_convert_rgb",
|
||||
"return_tensors",
|
||||
"data_format",
|
||||
"input_data_format"
|
||||
],
|
||||
"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 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"architectures": [
|
||||
"CLIPVisionModelWithProjection"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dropout": 0.0,
|
||||
"hidden_act": "quick_gelu",
|
||||
"hidden_size": 1024,
|
||||
"image_size": 224,
|
||||
"initializer_factor": 1.0,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"model_type": "clip_vision_model",
|
||||
"num_attention_heads": 16,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 24,
|
||||
"patch_size": 14,
|
||||
"projection_dim": 768,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.39.3"
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_class_name": "StableDiffusionImage2MVCustomPipeline",
|
||||
"_diffusers_version": "0.27.2",
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"condition_offset": true,
|
||||
"feature_extractor": [
|
||||
"transformers",
|
||||
"CLIPImageProcessor"
|
||||
],
|
||||
"image_encoder": [
|
||||
"transformers",
|
||||
"CLIPVisionModelWithProjection"
|
||||
],
|
||||
"requires_safety_checker": true,
|
||||
"safety_checker": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"DDIMScheduler"
|
||||
],
|
||||
"unet": [
|
||||
"diffusers",
|
||||
"UNet2DConditionModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"_class_name": "DDIMScheduler",
|
||||
"_diffusers_version": "0.27.2",
|
||||
"beta_end": 0.012,
|
||||
"beta_schedule": "scaled_linear",
|
||||
"beta_start": 0.00085,
|
||||
"clip_sample": false,
|
||||
"clip_sample_range": 1.0,
|
||||
"dynamic_thresholding_ratio": 0.995,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "epsilon",
|
||||
"rescale_betas_zero_snr": false,
|
||||
"sample_max_value": 1.0,
|
||||
"set_alpha_to_one": false,
|
||||
"skip_prk_steps": true,
|
||||
"steps_offset": 1,
|
||||
"thresholding": false,
|
||||
"timestep_spacing": "leading",
|
||||
"trained_betas": null
|
||||
}
|
||||
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"_class_name": "UnifieldWrappedUNet",
|
||||
"_diffusers_version": "0.27.2",
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"act_fn": "silu",
|
||||
"addition_embed_type": null,
|
||||
"addition_embed_type_num_heads": 64,
|
||||
"addition_time_embed_dim": null,
|
||||
"attention_head_dim": 8,
|
||||
"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": 768,
|
||||
"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": 8,
|
||||
"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": 8,
|
||||
"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": 64,
|
||||
"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": false,
|
||||
"use_linear_projection": false
|
||||
}
|
||||
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.27.2",
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"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": 256,
|
||||
"scaling_factor": 0.18215,
|
||||
"up_block_types": [
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D"
|
||||
]
|
||||
}
|
||||
+44
@@ -0,0 +1,44 @@
|
||||
{
|
||||
"_valid_processor_keys": [
|
||||
"images",
|
||||
"do_resize",
|
||||
"size",
|
||||
"resample",
|
||||
"do_center_crop",
|
||||
"crop_size",
|
||||
"do_rescale",
|
||||
"rescale_factor",
|
||||
"do_normalize",
|
||||
"image_mean",
|
||||
"image_std",
|
||||
"do_convert_rgb",
|
||||
"return_tensors",
|
||||
"data_format",
|
||||
"input_data_format"
|
||||
],
|
||||
"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 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"architectures": [
|
||||
"CLIPVisionModelWithProjection"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dropout": 0.0,
|
||||
"hidden_act": "quick_gelu",
|
||||
"hidden_size": 1024,
|
||||
"image_size": 224,
|
||||
"initializer_factor": 1.0,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"model_type": "clip_vision_model",
|
||||
"num_attention_heads": 16,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 24,
|
||||
"patch_size": 14,
|
||||
"projection_dim": 768,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.39.3"
|
||||
}
|
||||
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_class_name": "StableDiffusionImageCustomPipeline",
|
||||
"_diffusers_version": "0.27.2",
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"feature_extractor": [
|
||||
"transformers",
|
||||
"CLIPImageProcessor"
|
||||
],
|
||||
"image_encoder": [
|
||||
"transformers",
|
||||
"CLIPVisionModelWithProjection"
|
||||
],
|
||||
"noisy_cond_latents": false,
|
||||
"requires_safety_checker": true,
|
||||
"safety_checker": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"EulerAncestralDiscreteScheduler"
|
||||
],
|
||||
"unet": [
|
||||
"diffusers",
|
||||
"UNet2DConditionModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"_class_name": "EulerAncestralDiscreteScheduler",
|
||||
"_diffusers_version": "0.27.2",
|
||||
"beta_end": 0.012,
|
||||
"beta_schedule": "scaled_linear",
|
||||
"beta_start": 0.00085,
|
||||
"clip_sample": false,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "epsilon",
|
||||
"rescale_betas_zero_snr": false,
|
||||
"set_alpha_to_one": false,
|
||||
"skip_prk_steps": true,
|
||||
"steps_offset": 1,
|
||||
"timestep_spacing": "linspace",
|
||||
"trained_betas": null
|
||||
}
|
||||
@@ -0,0 +1,68 @@
|
||||
{
|
||||
"_class_name": "UnifieldWrappedUNet",
|
||||
"_diffusers_version": "0.27.2",
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"act_fn": "silu",
|
||||
"addition_embed_type": null,
|
||||
"addition_embed_type_num_heads": 64,
|
||||
"addition_time_embed_dim": null,
|
||||
"attention_head_dim": 8,
|
||||
"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": 768,
|
||||
"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": 64,
|
||||
"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": false,
|
||||
"use_linear_projection": false
|
||||
}
|
||||
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.27.2",
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"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": 256,
|
||||
"scaling_factor": 0.18215,
|
||||
"up_block_types": [
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,70 @@
|
||||
model:
|
||||
base_learning_rate: 1.0e-04
|
||||
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
||||
params:
|
||||
linear_start: 0.00085
|
||||
linear_end: 0.0120
|
||||
num_timesteps_cond: 1
|
||||
log_every_t: 200
|
||||
timesteps: 1000
|
||||
first_stage_key: "jpg"
|
||||
cond_stage_key: "txt"
|
||||
image_size: 64
|
||||
channels: 4
|
||||
cond_stage_trainable: false # Note: different from the one we trained before
|
||||
conditioning_key: crossattn
|
||||
monitor: val/loss_simple_ema
|
||||
scale_factor: 0.18215
|
||||
use_ema: False
|
||||
|
||||
scheduler_config: # 10000 warmup steps
|
||||
target: ldm.lr_scheduler.LambdaLinearScheduler
|
||||
params:
|
||||
warm_up_steps: [ 10000 ]
|
||||
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
||||
f_start: [ 1.e-6 ]
|
||||
f_max: [ 1. ]
|
||||
f_min: [ 1. ]
|
||||
|
||||
unet_config:
|
||||
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||||
params:
|
||||
image_size: 32 # unused
|
||||
in_channels: 4
|
||||
out_channels: 4
|
||||
model_channels: 320
|
||||
attention_resolutions: [ 4, 2, 1 ]
|
||||
num_res_blocks: 2
|
||||
channel_mult: [ 1, 2, 4, 4 ]
|
||||
num_heads: 8
|
||||
use_spatial_transformer: True
|
||||
transformer_depth: 1
|
||||
context_dim: 768
|
||||
use_checkpoint: True
|
||||
legacy: False
|
||||
|
||||
first_stage_config:
|
||||
target: ldm.models.autoencoder.AutoencoderKL
|
||||
params:
|
||||
embed_dim: 4
|
||||
monitor: val/rec_loss
|
||||
ddconfig:
|
||||
double_z: true
|
||||
z_channels: 4
|
||||
resolution: 256
|
||||
in_channels: 3
|
||||
out_ch: 3
|
||||
ch: 128
|
||||
ch_mult:
|
||||
- 1
|
||||
- 2
|
||||
- 4
|
||||
- 4
|
||||
num_res_blocks: 2
|
||||
attn_resolutions: []
|
||||
dropout: 0.0
|
||||
lossconfig:
|
||||
target: torch.nn.Identity
|
||||
|
||||
cond_stage_config:
|
||||
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
||||
@@ -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: openrail
|
||||
---
|
||||
# MVDream-diffusers Model Card
|
||||
This is a port of https://huggingface.co/Peng-Wang/ImageDream into diffusers.
|
||||
|
||||
For usage, please check: https://github.com/ashawkey/mvdream_diffusers
|
||||
## Citation
|
||||
```
|
||||
@article{wang2023imagedream,
|
||||
title={ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation},
|
||||
author={Wang, Peng and Shi, Yichun},
|
||||
journal={arXiv preprint arXiv:2312.02201},
|
||||
year={2023}
|
||||
}
|
||||
```
|
||||
## Misuse, Malicious Use, and Out-of-Scope Use
|
||||
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
|
||||
+29
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"crop_size": {
|
||||
"height": 224,
|
||||
"width": 224
|
||||
},
|
||||
"do_center_crop": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"feature_extractor_type": "CLIPFeatureExtractor",
|
||||
"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
|
||||
},
|
||||
"use_square_size": false
|
||||
}
|
||||
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
|
||||
"architectures": [
|
||||
"CLIPVisionModel"
|
||||
],
|
||||
"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": "4.35.2"
|
||||
}
|
||||
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"_class_name": "MVDreamPipeline",
|
||||
"_diffusers_version": "0.25.0",
|
||||
"feature_extractor": [
|
||||
"transformers",
|
||||
"CLIPImageProcessor"
|
||||
],
|
||||
"image_encoder": [
|
||||
"transformers",
|
||||
"CLIPVisionModel"
|
||||
],
|
||||
"requires_safety_checker": false,
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"DDIMScheduler"
|
||||
],
|
||||
"text_encoder": [
|
||||
"transformers",
|
||||
"CLIPTextModel"
|
||||
],
|
||||
"tokenizer": [
|
||||
"transformers",
|
||||
"CLIPTokenizer"
|
||||
],
|
||||
"unet": [
|
||||
"mv_unet",
|
||||
"MultiViewUNetModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,558 @@
|
||||
import torch
|
||||
import torch.nn.functional as F
|
||||
import inspect
|
||||
import numpy as np
|
||||
from typing import Callable, List, Optional, Union
|
||||
from transformers import CLIPTextModel, CLIPTokenizer, CLIPVisionModel, CLIPImageProcessor
|
||||
from diffusers import AutoencoderKL, DiffusionPipeline
|
||||
from diffusers.utils import (
|
||||
deprecate,
|
||||
is_accelerate_available,
|
||||
is_accelerate_version,
|
||||
logging,
|
||||
)
|
||||
from diffusers.configuration_utils import FrozenDict
|
||||
from diffusers.schedulers import DDIMScheduler
|
||||
from diffusers.utils.torch_utils import randn_tensor
|
||||
|
||||
from mv_unet import MultiViewUNetModel, get_camera
|
||||
|
||||
logger = logging.get_logger(__name__) # pylint: disable=invalid-name
|
||||
|
||||
|
||||
class MVDreamPipeline(DiffusionPipeline):
|
||||
|
||||
_optional_components = ["feature_extractor", "image_encoder"]
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
vae: AutoencoderKL,
|
||||
unet: MultiViewUNetModel,
|
||||
tokenizer: CLIPTokenizer,
|
||||
text_encoder: CLIPTextModel,
|
||||
scheduler: DDIMScheduler,
|
||||
# imagedream variant
|
||||
feature_extractor: CLIPImageProcessor,
|
||||
image_encoder: CLIPVisionModel,
|
||||
requires_safety_checker: bool = False,
|
||||
):
|
||||
super().__init__()
|
||||
|
||||
if hasattr(scheduler.config, "steps_offset") and scheduler.config.steps_offset != 1: # type: ignore
|
||||
deprecation_message = (
|
||||
f"The configuration file of this scheduler: {scheduler} is outdated. `steps_offset`"
|
||||
f" should be set to 1 instead of {scheduler.config.steps_offset}. Please make sure " # type: ignore
|
||||
"to update the config accordingly as leaving `steps_offset` might led to incorrect results"
|
||||
" in future versions. If you have downloaded this checkpoint from the Hugging Face Hub,"
|
||||
" it would be very nice if you could open a Pull request for the `scheduler/scheduler_config.json`"
|
||||
" file"
|
||||
)
|
||||
deprecate(
|
||||
"steps_offset!=1", "1.0.0", deprecation_message, standard_warn=False
|
||||
)
|
||||
new_config = dict(scheduler.config)
|
||||
new_config["steps_offset"] = 1
|
||||
scheduler._internal_dict = FrozenDict(new_config)
|
||||
|
||||
if hasattr(scheduler.config, "clip_sample") and scheduler.config.clip_sample is True: # type: ignore
|
||||
deprecation_message = (
|
||||
f"The configuration file of this scheduler: {scheduler} has not set the configuration `clip_sample`."
|
||||
" `clip_sample` should be set to False in the configuration file. Please make sure to update the"
|
||||
" config accordingly as not setting `clip_sample` in the config might lead to incorrect results in"
|
||||
" future versions. If you have downloaded this checkpoint from the Hugging Face Hub, it would be very"
|
||||
" nice if you could open a Pull request for the `scheduler/scheduler_config.json` file"
|
||||
)
|
||||
deprecate(
|
||||
"clip_sample not set", "1.0.0", deprecation_message, standard_warn=False
|
||||
)
|
||||
new_config = dict(scheduler.config)
|
||||
new_config["clip_sample"] = False
|
||||
scheduler._internal_dict = FrozenDict(new_config)
|
||||
|
||||
self.register_modules(
|
||||
vae=vae,
|
||||
unet=unet,
|
||||
scheduler=scheduler,
|
||||
tokenizer=tokenizer,
|
||||
text_encoder=text_encoder,
|
||||
feature_extractor=feature_extractor,
|
||||
image_encoder=image_encoder,
|
||||
)
|
||||
self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
|
||||
self.register_to_config(requires_safety_checker=requires_safety_checker)
|
||||
|
||||
def enable_vae_slicing(self):
|
||||
r"""
|
||||
Enable sliced VAE decoding.
|
||||
|
||||
When this option is enabled, the VAE will split the input tensor in slices to compute decoding in several
|
||||
steps. This is useful to save some memory and allow larger batch sizes.
|
||||
"""
|
||||
self.vae.enable_slicing()
|
||||
|
||||
def disable_vae_slicing(self):
|
||||
r"""
|
||||
Disable sliced VAE decoding. If `enable_vae_slicing` was previously invoked, this method will go back to
|
||||
computing decoding in one step.
|
||||
"""
|
||||
self.vae.disable_slicing()
|
||||
|
||||
def enable_vae_tiling(self):
|
||||
r"""
|
||||
Enable tiled VAE decoding.
|
||||
|
||||
When this option is enabled, the VAE will split the input tensor into tiles to compute decoding and encoding in
|
||||
several steps. This is useful to save a large amount of memory and to allow the processing of larger images.
|
||||
"""
|
||||
self.vae.enable_tiling()
|
||||
|
||||
def disable_vae_tiling(self):
|
||||
r"""
|
||||
Disable tiled VAE decoding. If `enable_vae_tiling` was previously invoked, this method will go back to
|
||||
computing decoding in one step.
|
||||
"""
|
||||
self.vae.disable_tiling()
|
||||
|
||||
def enable_sequential_cpu_offload(self, gpu_id=0):
|
||||
r"""
|
||||
Offloads all models to CPU using accelerate, significantly reducing memory usage. When called, unet,
|
||||
text_encoder, vae and safety checker have their state dicts saved to CPU and then are moved to a
|
||||
`torch.device('meta') and loaded to GPU only when their specific submodule has its `forward` method called.
|
||||
Note that offloading happens on a submodule basis. Memory savings are higher than with
|
||||
`enable_model_cpu_offload`, but performance is lower.
|
||||
"""
|
||||
if is_accelerate_available() and is_accelerate_version(">=", "0.14.0"):
|
||||
from accelerate import cpu_offload
|
||||
else:
|
||||
raise ImportError(
|
||||
"`enable_sequential_cpu_offload` requires `accelerate v0.14.0` or higher"
|
||||
)
|
||||
|
||||
device = torch.device(f"cuda:{gpu_id}")
|
||||
|
||||
if self.device.type != "cpu":
|
||||
self.to("cpu", silence_dtype_warnings=True)
|
||||
torch.cuda.empty_cache() # otherwise we don't see the memory savings (but they probably exist)
|
||||
|
||||
for cpu_offloaded_model in [self.unet, self.text_encoder, self.vae]:
|
||||
cpu_offload(cpu_offloaded_model, device)
|
||||
|
||||
def enable_model_cpu_offload(self, gpu_id=0):
|
||||
r"""
|
||||
Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared
|
||||
to `enable_sequential_cpu_offload`, this method moves one whole model at a time to the GPU when its `forward`
|
||||
method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with
|
||||
`enable_sequential_cpu_offload`, but performance is much better due to the iterative execution of the `unet`.
|
||||
"""
|
||||
if is_accelerate_available() and is_accelerate_version(">=", "0.17.0.dev0"):
|
||||
from accelerate import cpu_offload_with_hook
|
||||
else:
|
||||
raise ImportError(
|
||||
"`enable_model_offload` requires `accelerate v0.17.0` or higher."
|
||||
)
|
||||
|
||||
device = torch.device(f"cuda:{gpu_id}")
|
||||
|
||||
if self.device.type != "cpu":
|
||||
self.to("cpu", silence_dtype_warnings=True)
|
||||
torch.cuda.empty_cache() # otherwise we don't see the memory savings (but they probably exist)
|
||||
|
||||
hook = None
|
||||
for cpu_offloaded_model in [self.text_encoder, self.unet, self.vae]:
|
||||
_, hook = cpu_offload_with_hook(
|
||||
cpu_offloaded_model, device, prev_module_hook=hook
|
||||
)
|
||||
|
||||
# We'll offload the last model manually.
|
||||
self.final_offload_hook = hook
|
||||
|
||||
@property
|
||||
def _execution_device(self):
|
||||
r"""
|
||||
Returns the device on which the pipeline's models will be executed. After calling
|
||||
`pipeline.enable_sequential_cpu_offload()` the execution device can only be inferred from Accelerate's module
|
||||
hooks.
|
||||
"""
|
||||
if not hasattr(self.unet, "_hf_hook"):
|
||||
return self.device
|
||||
for module in self.unet.modules():
|
||||
if (
|
||||
hasattr(module, "_hf_hook")
|
||||
and hasattr(module._hf_hook, "execution_device")
|
||||
and module._hf_hook.execution_device is not None
|
||||
):
|
||||
return torch.device(module._hf_hook.execution_device)
|
||||
return self.device
|
||||
|
||||
def _encode_prompt(
|
||||
self,
|
||||
prompt,
|
||||
device,
|
||||
num_images_per_prompt,
|
||||
do_classifier_free_guidance: bool,
|
||||
negative_prompt=None,
|
||||
):
|
||||
r"""
|
||||
Encodes the prompt into text encoder hidden states.
|
||||
|
||||
Args:
|
||||
prompt (`str` or `List[str]`, *optional*):
|
||||
prompt to be encoded
|
||||
device: (`torch.device`):
|
||||
torch device
|
||||
num_images_per_prompt (`int`):
|
||||
number of images that should be generated per prompt
|
||||
do_classifier_free_guidance (`bool`):
|
||||
whether to use classifier free guidance or not
|
||||
negative_prompt (`str` or `List[str]`, *optional*):
|
||||
The prompt or prompts not to guide the image generation. If not defined, one has to pass
|
||||
`negative_prompt_embeds`. instead. If not defined, one has to pass `negative_prompt_embeds`. instead.
|
||||
Ignored when not using guidance (i.e., ignored if `guidance_scale` is less than `1`).
|
||||
prompt_embeds (`torch.FloatTensor`, *optional*):
|
||||
Pre-generated text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt weighting. If not
|
||||
provided, text embeddings will be generated from `prompt` input argument.
|
||||
negative_prompt_embeds (`torch.FloatTensor`, *optional*):
|
||||
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, *e.g.* prompt
|
||||
weighting. If not provided, negative_prompt_embeds will be generated from `negative_prompt` input
|
||||
argument.
|
||||
"""
|
||||
if prompt is not None and isinstance(prompt, str):
|
||||
batch_size = 1
|
||||
elif prompt is not None and isinstance(prompt, list):
|
||||
batch_size = len(prompt)
|
||||
else:
|
||||
raise ValueError(
|
||||
f"`prompt` should be either a string or a list of strings, but got {type(prompt)}."
|
||||
)
|
||||
|
||||
text_inputs = self.tokenizer(
|
||||
prompt,
|
||||
padding="max_length",
|
||||
max_length=self.tokenizer.model_max_length,
|
||||
truncation=True,
|
||||
return_tensors="pt",
|
||||
)
|
||||
text_input_ids = text_inputs.input_ids
|
||||
untruncated_ids = self.tokenizer(
|
||||
prompt, padding="longest", return_tensors="pt"
|
||||
).input_ids
|
||||
|
||||
if untruncated_ids.shape[-1] >= text_input_ids.shape[-1] and not torch.equal(
|
||||
text_input_ids, untruncated_ids
|
||||
):
|
||||
removed_text = self.tokenizer.batch_decode(
|
||||
untruncated_ids[:, self.tokenizer.model_max_length - 1 : -1]
|
||||
)
|
||||
logger.warning(
|
||||
"The following part of your input was truncated because CLIP can only handle sequences up to"
|
||||
f" {self.tokenizer.model_max_length} tokens: {removed_text}"
|
||||
)
|
||||
|
||||
if (
|
||||
hasattr(self.text_encoder.config, "use_attention_mask")
|
||||
and self.text_encoder.config.use_attention_mask
|
||||
):
|
||||
attention_mask = text_inputs.attention_mask.to(device)
|
||||
else:
|
||||
attention_mask = None
|
||||
|
||||
prompt_embeds = self.text_encoder(
|
||||
text_input_ids.to(device),
|
||||
attention_mask=attention_mask,
|
||||
)
|
||||
prompt_embeds = prompt_embeds[0]
|
||||
|
||||
prompt_embeds = prompt_embeds.to(dtype=self.text_encoder.dtype, device=device)
|
||||
|
||||
bs_embed, seq_len, _ = prompt_embeds.shape
|
||||
# duplicate text embeddings for each generation per prompt, using mps friendly method
|
||||
prompt_embeds = prompt_embeds.repeat(1, num_images_per_prompt, 1)
|
||||
prompt_embeds = prompt_embeds.view(
|
||||
bs_embed * num_images_per_prompt, seq_len, -1
|
||||
)
|
||||
|
||||
# get unconditional embeddings for classifier free guidance
|
||||
if do_classifier_free_guidance:
|
||||
uncond_tokens: List[str]
|
||||
if negative_prompt is None:
|
||||
uncond_tokens = [""] * batch_size
|
||||
elif type(prompt) is not type(negative_prompt):
|
||||
raise TypeError(
|
||||
f"`negative_prompt` should be the same type to `prompt`, but got {type(negative_prompt)} !="
|
||||
f" {type(prompt)}."
|
||||
)
|
||||
elif isinstance(negative_prompt, str):
|
||||
uncond_tokens = [negative_prompt]
|
||||
elif batch_size != len(negative_prompt):
|
||||
raise ValueError(
|
||||
f"`negative_prompt`: {negative_prompt} has batch size {len(negative_prompt)}, but `prompt`:"
|
||||
f" {prompt} has batch size {batch_size}. Please make sure that passed `negative_prompt` matches"
|
||||
" the batch size of `prompt`."
|
||||
)
|
||||
else:
|
||||
uncond_tokens = negative_prompt
|
||||
|
||||
max_length = prompt_embeds.shape[1]
|
||||
uncond_input = self.tokenizer(
|
||||
uncond_tokens,
|
||||
padding="max_length",
|
||||
max_length=max_length,
|
||||
truncation=True,
|
||||
return_tensors="pt",
|
||||
)
|
||||
|
||||
if (
|
||||
hasattr(self.text_encoder.config, "use_attention_mask")
|
||||
and self.text_encoder.config.use_attention_mask
|
||||
):
|
||||
attention_mask = uncond_input.attention_mask.to(device)
|
||||
else:
|
||||
attention_mask = None
|
||||
|
||||
negative_prompt_embeds = self.text_encoder(
|
||||
uncond_input.input_ids.to(device),
|
||||
attention_mask=attention_mask,
|
||||
)
|
||||
negative_prompt_embeds = negative_prompt_embeds[0]
|
||||
|
||||
# duplicate unconditional embeddings for each generation per prompt, using mps friendly method
|
||||
seq_len = negative_prompt_embeds.shape[1]
|
||||
|
||||
negative_prompt_embeds = negative_prompt_embeds.to(
|
||||
dtype=self.text_encoder.dtype, device=device
|
||||
)
|
||||
|
||||
negative_prompt_embeds = negative_prompt_embeds.repeat(
|
||||
1, num_images_per_prompt, 1
|
||||
)
|
||||
negative_prompt_embeds = negative_prompt_embeds.view(
|
||||
batch_size * num_images_per_prompt, seq_len, -1
|
||||
)
|
||||
|
||||
# For classifier free guidance, we need to do two forward passes.
|
||||
# Here we concatenate the unconditional and text embeddings into a single batch
|
||||
# to avoid doing two forward passes
|
||||
prompt_embeds = torch.cat([negative_prompt_embeds, prompt_embeds])
|
||||
|
||||
return prompt_embeds
|
||||
|
||||
def decode_latents(self, latents):
|
||||
latents = 1 / self.vae.config.scaling_factor * latents
|
||||
image = self.vae.decode(latents).sample
|
||||
image = (image / 2 + 0.5).clamp(0, 1)
|
||||
# we always cast to float32 as this does not cause significant overhead and is compatible with bfloat16
|
||||
image = image.cpu().permute(0, 2, 3, 1).float().numpy()
|
||||
return image
|
||||
|
||||
def prepare_extra_step_kwargs(self, generator, eta):
|
||||
# prepare extra kwargs for the scheduler step, since not all schedulers have the same signature
|
||||
# eta (η) is only used with the DDIMScheduler, it will be ignored for other schedulers.
|
||||
# eta corresponds to η in DDIM paper: https://arxiv.org/abs/2010.02502
|
||||
# and should be between [0, 1]
|
||||
|
||||
accepts_eta = "eta" in set(
|
||||
inspect.signature(self.scheduler.step).parameters.keys()
|
||||
)
|
||||
extra_step_kwargs = {}
|
||||
if accepts_eta:
|
||||
extra_step_kwargs["eta"] = eta
|
||||
|
||||
# check if the scheduler accepts generator
|
||||
accepts_generator = "generator" in set(
|
||||
inspect.signature(self.scheduler.step).parameters.keys()
|
||||
)
|
||||
if accepts_generator:
|
||||
extra_step_kwargs["generator"] = generator
|
||||
return extra_step_kwargs
|
||||
|
||||
def prepare_latents(
|
||||
self,
|
||||
batch_size,
|
||||
num_channels_latents,
|
||||
height,
|
||||
width,
|
||||
dtype,
|
||||
device,
|
||||
generator,
|
||||
latents=None,
|
||||
):
|
||||
shape = (
|
||||
batch_size,
|
||||
num_channels_latents,
|
||||
height // self.vae_scale_factor,
|
||||
width // self.vae_scale_factor,
|
||||
)
|
||||
if isinstance(generator, list) and len(generator) != batch_size:
|
||||
raise ValueError(
|
||||
f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
|
||||
f" size of {batch_size}. Make sure the batch size matches the length of the generators."
|
||||
)
|
||||
|
||||
if latents is None:
|
||||
latents = randn_tensor(
|
||||
shape, generator=generator, device=device, dtype=dtype
|
||||
)
|
||||
else:
|
||||
latents = latents.to(device)
|
||||
|
||||
# scale the initial noise by the standard deviation required by the scheduler
|
||||
latents = latents * self.scheduler.init_noise_sigma
|
||||
return latents
|
||||
|
||||
def encode_image(self, image, device, num_images_per_prompt):
|
||||
dtype = next(self.image_encoder.parameters()).dtype
|
||||
|
||||
if image.dtype == np.float32:
|
||||
image = (image * 255).astype(np.uint8)
|
||||
|
||||
image = self.feature_extractor(image, return_tensors="pt").pixel_values
|
||||
image = image.to(device=device, dtype=dtype)
|
||||
|
||||
image_embeds = self.image_encoder(image, output_hidden_states=True).hidden_states[-2]
|
||||
image_embeds = image_embeds.repeat_interleave(num_images_per_prompt, dim=0)
|
||||
|
||||
return torch.zeros_like(image_embeds), image_embeds
|
||||
|
||||
def encode_image_latents(self, image, device, num_images_per_prompt):
|
||||
|
||||
dtype = next(self.image_encoder.parameters()).dtype
|
||||
|
||||
image = torch.from_numpy(image).unsqueeze(0).permute(0, 3, 1, 2).to(device=device) # [1, 3, H, W]
|
||||
image = 2 * image - 1
|
||||
image = F.interpolate(image, (256, 256), mode='bilinear', align_corners=False)
|
||||
image = image.to(dtype=dtype)
|
||||
|
||||
posterior = self.vae.encode(image).latent_dist
|
||||
latents = posterior.sample() * self.vae.config.scaling_factor # [B, C, H, W]
|
||||
latents = latents.repeat_interleave(num_images_per_prompt, dim=0)
|
||||
|
||||
return torch.zeros_like(latents), latents
|
||||
|
||||
@torch.no_grad()
|
||||
def __call__(
|
||||
self,
|
||||
prompt: str = "",
|
||||
image: Optional[np.ndarray] = None,
|
||||
height: int = 256,
|
||||
width: int = 256,
|
||||
num_inference_steps: int = 50,
|
||||
guidance_scale: float = 7.0,
|
||||
negative_prompt: str = "",
|
||||
num_images_per_prompt: int = 1,
|
||||
eta: float = 0.0,
|
||||
generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
|
||||
output_type: Optional[str] = "numpy", # pil, numpy, latents
|
||||
callback: Optional[Callable[[int, int, torch.FloatTensor], None]] = None,
|
||||
callback_steps: int = 1,
|
||||
num_frames: int = 4,
|
||||
device=torch.device("cuda:0"),
|
||||
):
|
||||
self.unet = self.unet.to(device=device)
|
||||
self.vae = self.vae.to(device=device)
|
||||
self.text_encoder = self.text_encoder.to(device=device)
|
||||
|
||||
# here `guidance_scale` is defined analog to the guidance weight `w` of equation (2)
|
||||
# of the Imagen paper: https://arxiv.org/pdf/2205.11487.pdf . `guidance_scale = 1`
|
||||
# corresponds to doing no classifier free guidance.
|
||||
do_classifier_free_guidance = guidance_scale > 1.0
|
||||
|
||||
# Prepare timesteps
|
||||
self.scheduler.set_timesteps(num_inference_steps, device=device)
|
||||
timesteps = self.scheduler.timesteps
|
||||
|
||||
# imagedream variant
|
||||
if image is not None:
|
||||
assert isinstance(image, np.ndarray) and image.dtype == np.float32
|
||||
self.image_encoder = self.image_encoder.to(device=device)
|
||||
image_embeds_neg, image_embeds_pos = self.encode_image(image, device, num_images_per_prompt)
|
||||
image_latents_neg, image_latents_pos = self.encode_image_latents(image, device, num_images_per_prompt)
|
||||
|
||||
_prompt_embeds = self._encode_prompt(
|
||||
prompt=prompt,
|
||||
device=device,
|
||||
num_images_per_prompt=num_images_per_prompt,
|
||||
do_classifier_free_guidance=do_classifier_free_guidance,
|
||||
negative_prompt=negative_prompt,
|
||||
) # type: ignore
|
||||
prompt_embeds_neg, prompt_embeds_pos = _prompt_embeds.chunk(2)
|
||||
|
||||
# Prepare latent variables
|
||||
actual_num_frames = num_frames if image is None else num_frames + 1
|
||||
latents: torch.Tensor = self.prepare_latents(
|
||||
actual_num_frames * num_images_per_prompt,
|
||||
4,
|
||||
height,
|
||||
width,
|
||||
prompt_embeds_pos.dtype,
|
||||
device,
|
||||
generator,
|
||||
None,
|
||||
)
|
||||
|
||||
if image is not None:
|
||||
camera = get_camera(num_frames, elevation=5, extra_view=True).to(dtype=latents.dtype, device=device)
|
||||
else:
|
||||
camera = get_camera(num_frames, elevation=15, extra_view=False).to(dtype=latents.dtype, device=device)
|
||||
camera = camera.repeat_interleave(num_images_per_prompt, dim=0)
|
||||
|
||||
# Prepare extra step kwargs.
|
||||
extra_step_kwargs = self.prepare_extra_step_kwargs(generator, eta)
|
||||
|
||||
# Denoising loop
|
||||
num_warmup_steps = len(timesteps) - num_inference_steps * self.scheduler.order
|
||||
with self.progress_bar(total=num_inference_steps) as progress_bar:
|
||||
for i, t in enumerate(timesteps):
|
||||
# expand the latents if we are doing classifier free guidance
|
||||
multiplier = 2 if do_classifier_free_guidance else 1
|
||||
latent_model_input = torch.cat([latents] * multiplier)
|
||||
latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
|
||||
|
||||
unet_inputs = {
|
||||
'x': latent_model_input,
|
||||
'timesteps': torch.tensor([t] * actual_num_frames * multiplier, dtype=latent_model_input.dtype, device=device),
|
||||
'context': torch.cat([prompt_embeds_neg] * actual_num_frames + [prompt_embeds_pos] * actual_num_frames),
|
||||
'num_frames': actual_num_frames,
|
||||
'camera': torch.cat([camera] * multiplier),
|
||||
}
|
||||
|
||||
if image is not None:
|
||||
unet_inputs['ip'] = torch.cat([image_embeds_neg] * actual_num_frames + [image_embeds_pos] * actual_num_frames)
|
||||
unet_inputs['ip_img'] = torch.cat([image_latents_neg] + [image_latents_pos]) # no repeat
|
||||
|
||||
# predict the noise residual
|
||||
noise_pred = self.unet.forward(**unet_inputs)
|
||||
|
||||
# perform guidance
|
||||
if do_classifier_free_guidance:
|
||||
noise_pred_uncond, noise_pred_text = noise_pred.chunk(2)
|
||||
noise_pred = noise_pred_uncond + guidance_scale * (
|
||||
noise_pred_text - noise_pred_uncond
|
||||
)
|
||||
|
||||
# compute the previous noisy sample x_t -> x_t-1
|
||||
latents: torch.Tensor = self.scheduler.step(
|
||||
noise_pred, t, latents, **extra_step_kwargs, return_dict=False
|
||||
)[0]
|
||||
|
||||
# call the callback, if provided
|
||||
if i == len(timesteps) - 1 or (
|
||||
(i + 1) > num_warmup_steps and (i + 1) % self.scheduler.order == 0
|
||||
):
|
||||
progress_bar.update()
|
||||
if callback is not None and i % callback_steps == 0:
|
||||
callback(i, t, latents) # type: ignore
|
||||
|
||||
# Post-processing
|
||||
if output_type == "latent":
|
||||
image = latents
|
||||
elif output_type == "pil":
|
||||
image = self.decode_latents(latents)
|
||||
image = self.numpy_to_pil(image)
|
||||
else: # numpy
|
||||
image = self.decode_latents(latents)
|
||||
|
||||
# Offload last model to CPU
|
||||
if hasattr(self, "final_offload_hook") and self.final_offload_hook is not None:
|
||||
self.final_offload_hook.offload()
|
||||
|
||||
return image
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"_class_name": "DDIMScheduler",
|
||||
"_diffusers_version": "0.25.0",
|
||||
"beta_end": 0.012,
|
||||
"beta_schedule": "scaled_linear",
|
||||
"beta_start": 0.00085,
|
||||
"clip_sample": false,
|
||||
"clip_sample_range": 1.0,
|
||||
"dynamic_thresholding_ratio": 0.995,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "epsilon",
|
||||
"rescale_betas_zero_snr": false,
|
||||
"sample_max_value": 1.0,
|
||||
"set_alpha_to_one": false,
|
||||
"steps_offset": 1,
|
||||
"thresholding": false,
|
||||
"timestep_spacing": "leading",
|
||||
"trained_betas": null
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "stabilityai/stable-diffusion-2-1",
|
||||
"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": "float16",
|
||||
"transformers_version": "4.35.2",
|
||||
"vocab_size": 49408
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
+24
@@ -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
|
||||
}
|
||||
}
|
||||
+38
@@ -0,0 +1,38 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "!",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"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": true,
|
||||
"do_lower_case": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 77,
|
||||
"pad_token": "!",
|
||||
"tokenizer_class": "CLIPTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_class_name": "MultiViewUNetModel",
|
||||
"_diffusers_version": "0.25.0",
|
||||
"attention_resolutions": [
|
||||
4,
|
||||
2,
|
||||
1
|
||||
],
|
||||
"camera_dim": 16,
|
||||
"channel_mult": [
|
||||
1,
|
||||
2,
|
||||
4,
|
||||
4
|
||||
],
|
||||
"context_dim": 1024,
|
||||
"image_size": 32,
|
||||
"in_channels": 4,
|
||||
"ip_dim": 16,
|
||||
"model_channels": 320,
|
||||
"num_head_channels": 64,
|
||||
"num_res_blocks": 2,
|
||||
"out_channels": 4,
|
||||
"transformer_depth": 1
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.25.0",
|
||||
"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,
|
||||
"layers_per_block": 2,
|
||||
"norm_num_groups": 32,
|
||||
"out_channels": 3,
|
||||
"sample_size": 256,
|
||||
"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 +1,3 @@
|
||||
---
|
||||
license: agpl-3.0
|
||||
---
|
||||
+28
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"crop_size": {
|
||||
"height": 224,
|
||||
"width": 224
|
||||
},
|
||||
"do_center_crop": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"feature_extractor_type": "CLIPFeatureExtractor",
|
||||
"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 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"architectures": [
|
||||
"CLIPVisionModelWithProjection"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"dropout": 0.0,
|
||||
"hidden_act": "quick_gelu",
|
||||
"hidden_size": 1024,
|
||||
"image_size": 224,
|
||||
"initializer_factor": 1.0,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"model_type": "clip_vision_model",
|
||||
"num_attention_heads": 16,
|
||||
"num_channels": 3,
|
||||
"num_hidden_layers": 24,
|
||||
"patch_size": 14,
|
||||
"projection_dim": 768,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.34.1"
|
||||
}
|
||||
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_class_name": "MVDiffusionImagePipeline",
|
||||
"_diffusers_version": "0.19.3",
|
||||
"feature_extractor": [
|
||||
"transformers",
|
||||
"CLIPImageProcessor"
|
||||
],
|
||||
"image_encoder": [
|
||||
"transformers",
|
||||
"CLIPVisionModelWithProjection"
|
||||
],
|
||||
"requires_safety_checker": true,
|
||||
"safety_checker": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"DDIMScheduler"
|
||||
],
|
||||
"unet": [
|
||||
"Wonder3D.models.unet_mv2d_condition",
|
||||
"UNetMV2DConditionModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"_class_name": "DDIMScheduler",
|
||||
"_diffusers_version": "0.19.3",
|
||||
"beta_end": 0.012,
|
||||
"beta_schedule": "scaled_linear",
|
||||
"beta_start": 0.00085,
|
||||
"clip_sample": false,
|
||||
"clip_sample_range": 1.0,
|
||||
"dynamic_thresholding_ratio": 0.995,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "epsilon",
|
||||
"rescale_betas_zero_snr": false,
|
||||
"sample_max_value": 1.0,
|
||||
"set_alpha_to_one": false,
|
||||
"skip_prk_steps": true,
|
||||
"steps_offset": 1,
|
||||
"thresholding": false,
|
||||
"timestep_spacing": "leading",
|
||||
"trained_betas": null
|
||||
}
|
||||
@@ -0,0 +1,74 @@
|
||||
{
|
||||
"_class_name": "UNetMV2DConditionModel",
|
||||
"_diffusers_version": "0.19.3",
|
||||
"_name_or_path": "/home/xiaoxiao/Workplace/wonder3Dplus/ckpts",
|
||||
"act_fn": "silu",
|
||||
"addition_embed_type": null,
|
||||
"addition_embed_type_num_heads": 64,
|
||||
"addition_time_embed_dim": null,
|
||||
"attention_head_dim": 8,
|
||||
"block_out_channels": [
|
||||
320,
|
||||
640,
|
||||
1280,
|
||||
1280
|
||||
],
|
||||
"cd_attention_last": false,
|
||||
"cd_attention_mid": true,
|
||||
"center_input_sample": false,
|
||||
"class_embed_type": "projection",
|
||||
"class_embeddings_concat": false,
|
||||
"conv_in_kernel": 3,
|
||||
"conv_out_kernel": 3,
|
||||
"cross_attention_dim": 768,
|
||||
"cross_attention_norm": null,
|
||||
"cross_domain_attention": false,
|
||||
"down_block_types": [
|
||||
"CrossAttnDownBlockMV2D",
|
||||
"CrossAttnDownBlockMV2D",
|
||||
"CrossAttnDownBlockMV2D",
|
||||
"DownBlock2D"
|
||||
],
|
||||
"downsample_padding": 1,
|
||||
"dual_cross_attention": false,
|
||||
"encoder_hid_dim": null,
|
||||
"encoder_hid_dim_type": null,
|
||||
"flip_sin_to_cos": true,
|
||||
"freq_shift": 0,
|
||||
"in_channels": 8,
|
||||
"joint_attention": false,
|
||||
"joint_attention_twice": true,
|
||||
"layers_per_block": 2,
|
||||
"mid_block_only_cross_attention": null,
|
||||
"mid_block_scale_factor": 1,
|
||||
"mid_block_type": "UNetMidBlockMV2DCrossAttn",
|
||||
"multiview_attention": true,
|
||||
"mvcd_attention": false,
|
||||
"norm_eps": 1e-05,
|
||||
"norm_num_groups": 32,
|
||||
"num_attention_heads": null,
|
||||
"num_class_embeds": null,
|
||||
"num_views": 6,
|
||||
"only_cross_attention": false,
|
||||
"out_channels": 4,
|
||||
"projection_class_embeddings_input_dim": 10,
|
||||
"resnet_out_scale_factor": 1.0,
|
||||
"resnet_skip_time_act": false,
|
||||
"resnet_time_scale_shift": "default",
|
||||
"sample_size": 32,
|
||||
"sparse_mv_attention": false,
|
||||
"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",
|
||||
"CrossAttnUpBlockMV2D",
|
||||
"CrossAttnUpBlockMV2D",
|
||||
"CrossAttnUpBlockMV2D"
|
||||
],
|
||||
"upcast_attention": false,
|
||||
"use_linear_projection": false
|
||||
}
|
||||
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.19.3",
|
||||
"_name_or_path": "lambdalabs/sd-image-variations-diffusers",
|
||||
"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,
|
||||
"layers_per_block": 2,
|
||||
"norm_num_groups": 32,
|
||||
"out_channels": 3,
|
||||
"sample_size": 256,
|
||||
"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 +1,3 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
+27
@@ -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 +1,23 @@
|
||||
{
|
||||
"_name_or_path": "stabilityai/stable-diffusion-2-1-unclip",
|
||||
"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": "4.37.2"
|
||||
}
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"_class_name": "DDPMScheduler",
|
||||
"_diffusers_version": "0.26.0.dev0",
|
||||
"beta_end": 0.02,
|
||||
"beta_schedule": "squaredcos_cap_v2",
|
||||
"beta_start": 0.0001,
|
||||
"clip_sample": true,
|
||||
"clip_sample_range": 1.0,
|
||||
"dynamic_thresholding_ratio": 0.995,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "epsilon",
|
||||
"rescale_betas_zero_snr": false,
|
||||
"sample_max_value": 1.0,
|
||||
"steps_offset": 0,
|
||||
"thresholding": false,
|
||||
"timestep_spacing": "leading",
|
||||
"trained_betas": null,
|
||||
"variance_type": "fixed_small"
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_class_name": "StableUnCLIPImageNormalizer",
|
||||
"_diffusers_version": "0.26.0.dev0",
|
||||
"_name_or_path": "stabilityai/stable-diffusion-2-1-unclip",
|
||||
"embedding_dim": 1024
|
||||
}
|
||||
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"_class_name": "StableUnCLIPImg2ImgPipeline",
|
||||
"_diffusers_version": "0.26.0.dev0",
|
||||
"feature_extractor": [
|
||||
"transformers",
|
||||
"CLIPImageProcessor"
|
||||
],
|
||||
"image_encoder": [
|
||||
"transformers",
|
||||
"CLIPVisionModelWithProjection"
|
||||
],
|
||||
"image_noising_scheduler": [
|
||||
"diffusers",
|
||||
"DDPMScheduler"
|
||||
],
|
||||
"image_normalizer": [
|
||||
"stable_diffusion",
|
||||
"StableUnCLIPImageNormalizer"
|
||||
],
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"DDIMScheduler"
|
||||
],
|
||||
"text_encoder": [
|
||||
"transformers",
|
||||
"CLIPTextModel"
|
||||
],
|
||||
"tokenizer": [
|
||||
"transformers",
|
||||
"CLIPTokenizer"
|
||||
],
|
||||
"unet": [
|
||||
"Era3D.mvdiffusion.models.unet_mv2d_condition",
|
||||
"UNetMV2DConditionModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
{
|
||||
"_class_name": "DDIMScheduler",
|
||||
"_diffusers_version": "0.26.0.dev0",
|
||||
"beta_end": 0.012,
|
||||
"beta_schedule": "linear",
|
||||
"beta_start": 0.00085,
|
||||
"clip_sample": false,
|
||||
"clip_sample_range": 1.0,
|
||||
"dynamic_thresholding_ratio": 0.995,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "v_prediction",
|
||||
"rescale_betas_zero_snr": false,
|
||||
"sample_max_value": 1.0,
|
||||
"set_alpha_to_one": false,
|
||||
"skip_prk_steps": true,
|
||||
"steps_offset": 1,
|
||||
"thresholding": false,
|
||||
"timestep_spacing": "leading",
|
||||
"trained_betas": null
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "stabilityai/stable-diffusion-2-1-unclip",
|
||||
"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": "float16",
|
||||
"transformers_version": "4.37.2",
|
||||
"vocab_size": 49408
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
+24
@@ -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 +1,38 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "!",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"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": true,
|
||||
"do_lower_case": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 77,
|
||||
"pad_token": "!",
|
||||
"tokenizer_class": "CLIPTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,95 @@
|
||||
{
|
||||
"_class_name": "UNetMV2DConditionModel",
|
||||
"_diffusers_version": "0.26.0.dev0",
|
||||
"_name_or_path": "../checkpoint_backup/output/unit-unclip-512-6view-randomele-self+row-8w-selfcd-rowmv-2block-linear-depthfilter-step-removewh-bs256-three/checkpoint-40000/unet_ema",
|
||||
"act_fn": "silu",
|
||||
"addition_channels": [
|
||||
1280,
|
||||
1280,
|
||||
1280
|
||||
],
|
||||
"addition_downsample": false,
|
||||
"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
|
||||
],
|
||||
"cd_attention_last": false,
|
||||
"cd_attention_mid": false,
|
||||
"center_input_sample": false,
|
||||
"class_embed_type": "projection",
|
||||
"class_embeddings_concat": false,
|
||||
"conv_in_kernel": 3,
|
||||
"conv_out_kernel": 3,
|
||||
"cross_attention_dim": 1024,
|
||||
"cross_attention_norm": null,
|
||||
"decay": 0.9999,
|
||||
"down_block_types": [
|
||||
"CrossAttnDownBlockMV2D",
|
||||
"CrossAttnDownBlockMV2D",
|
||||
"CrossAttnDownBlockMV2D",
|
||||
"DownBlock2D"
|
||||
],
|
||||
"downsample_padding": 1,
|
||||
"dual_cross_attention": false,
|
||||
"encoder_hid_dim": null,
|
||||
"encoder_hid_dim_type": null,
|
||||
"flip_sin_to_cos": true,
|
||||
"freq_shift": 0,
|
||||
"in_channels": 8,
|
||||
"inv_gamma": 1.0,
|
||||
"layers_per_block": 2,
|
||||
"mid_block_only_cross_attention": null,
|
||||
"mid_block_scale_factor": 1,
|
||||
"mid_block_type": "UNetMidBlockMV2DCrossAttn",
|
||||
"min_decay": 0.0,
|
||||
"multiview_attention": true,
|
||||
"mvcd_attention": true,
|
||||
"norm_eps": 1e-05,
|
||||
"norm_num_groups": 32,
|
||||
"num_attention_heads": null,
|
||||
"num_class_embeds": null,
|
||||
"num_regress_blocks": 3,
|
||||
"num_views": 6,
|
||||
"only_cross_attention": false,
|
||||
"optimization_step": 40000,
|
||||
"out_channels": 4,
|
||||
"power": 0.6666666666666666,
|
||||
"projection_camera_embeddings_input_dim": 4,
|
||||
"projection_class_embeddings_input_dim": 2048,
|
||||
"regress_elevation": true,
|
||||
"regress_focal_length": true,
|
||||
"resnet_out_scale_factor": 1.0,
|
||||
"resnet_skip_time_act": false,
|
||||
"resnet_time_scale_shift": "default",
|
||||
"sample_size": 64,
|
||||
"selfattn_block": "self_rowwise",
|
||||
"sparse_mv_attention": true,
|
||||
"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",
|
||||
"CrossAttnUpBlockMV2D",
|
||||
"CrossAttnUpBlockMV2D",
|
||||
"CrossAttnUpBlockMV2D"
|
||||
],
|
||||
"upcast_attention": true,
|
||||
"update_after_step": 0,
|
||||
"use_dino": false,
|
||||
"use_ema_warmup": false,
|
||||
"use_linear_projection": true
|
||||
}
|
||||
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.26.0.dev0",
|
||||
"_name_or_path": "stabilityai/stable-diffusion-2-1-unclip",
|
||||
"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,
|
||||
"layers_per_block": 2,
|
||||
"norm_num_groups": 32,
|
||||
"out_channels": 3,
|
||||
"sample_size": 768,
|
||||
"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
|
||||
+27
@@ -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
|
||||
}
|
||||
}
|
||||
+19
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"crop_size": {
|
||||
"height": 512,
|
||||
"width": 512
|
||||
},
|
||||
"do_center_crop": true,
|
||||
"do_convert_rgb": true,
|
||||
"do_normalize": true,
|
||||
"do_rescale": true,
|
||||
"do_resize": true,
|
||||
"image_mean": 0.5,
|
||||
"image_processor_type": "CLIPImageProcessor",
|
||||
"image_std": 0.8,
|
||||
"resample": 2,
|
||||
"rescale_factor": 0.00392156862745098,
|
||||
"size": {
|
||||
"shortest_edge": 512
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,120 @@
|
||||
{
|
||||
"_class_name": "Zero123PlusPipeline",
|
||||
"_diffusers_version": "0.24.0",
|
||||
"_name_or_path": "sudo-ai/zero123plus-v1.1",
|
||||
"feature_extractor_clip": [
|
||||
"transformers",
|
||||
"CLIPImageProcessor"
|
||||
],
|
||||
"feature_extractor_vae": [
|
||||
"transformers",
|
||||
"CLIPImageProcessor"
|
||||
],
|
||||
"ramping_coefficients": [
|
||||
0.00301829120144248,
|
||||
0.2204633206129074,
|
||||
0.21527841687202454,
|
||||
0.23498539626598358,
|
||||
0.1914631873369217,
|
||||
0.20188239216804504,
|
||||
0.19352824985980988,
|
||||
0.17249998450279236,
|
||||
0.15826298296451569,
|
||||
0.15236389636993408,
|
||||
0.13444548845291138,
|
||||
0.12044154852628708,
|
||||
0.12808501720428467,
|
||||
0.1271015852689743,
|
||||
0.13629068434238434,
|
||||
0.14516159892082214,
|
||||
0.15645112097263336,
|
||||
0.16885493695735931,
|
||||
0.18022602796554565,
|
||||
0.1958882212638855,
|
||||
0.21415705978870392,
|
||||
0.23056700825691223,
|
||||
0.2505834102630615,
|
||||
0.2574525773525238,
|
||||
0.275470107793808,
|
||||
0.2808215022087097,
|
||||
0.29953837394714355,
|
||||
0.2967497408390045,
|
||||
0.2883710563182831,
|
||||
0.3023308515548706,
|
||||
0.3054688572883606,
|
||||
0.32596179842948914,
|
||||
0.3225354254245758,
|
||||
0.3140765428543091,
|
||||
0.3288663625717163,
|
||||
0.3435625731945038,
|
||||
0.3342442810535431,
|
||||
0.32937031984329224,
|
||||
0.35734811425209045,
|
||||
0.3601177930831909,
|
||||
0.3517529368400574,
|
||||
0.3810708224773407,
|
||||
0.40007662773132324,
|
||||
0.4264647364616394,
|
||||
0.3977527916431427,
|
||||
0.4314143657684326,
|
||||
0.49558719992637634,
|
||||
0.4665665030479431,
|
||||
0.48960328102111816,
|
||||
0.5141982436180115,
|
||||
0.5230164527893066,
|
||||
0.5266074538230896,
|
||||
0.5456079840660095,
|
||||
0.5737904906272888,
|
||||
0.5882097482681274,
|
||||
0.6210350394248962,
|
||||
0.6530380845069885,
|
||||
0.6383244395256042,
|
||||
0.6792004704475403,
|
||||
0.6567418575286865,
|
||||
0.7517656683921814,
|
||||
0.736494243144989,
|
||||
0.7586457133293152,
|
||||
0.8130561709403992,
|
||||
0.9578766226768494,
|
||||
1.001284122467041,
|
||||
0.9404520988464355,
|
||||
1.004292368888855,
|
||||
0.9145274758338928,
|
||||
0.9771682620048523,
|
||||
1.0350638628005981,
|
||||
1.0265849828720093,
|
||||
1.0594775676727295,
|
||||
0.980824887752533,
|
||||
1.0715670585632324,
|
||||
1.0140161514282227,
|
||||
1.1983819007873535
|
||||
],
|
||||
"safety_checker": [
|
||||
null,
|
||||
null
|
||||
],
|
||||
"scheduler": [
|
||||
"diffusers",
|
||||
"EulerAncestralDiscreteScheduler"
|
||||
],
|
||||
"text_encoder": [
|
||||
"transformers",
|
||||
"CLIPTextModel"
|
||||
],
|
||||
"tokenizer": [
|
||||
"transformers",
|
||||
"CLIPTokenizer"
|
||||
],
|
||||
"unet": [
|
||||
"diffusers",
|
||||
"UNet2DConditionModel"
|
||||
],
|
||||
"vae": [
|
||||
"diffusers",
|
||||
"AutoencoderKL"
|
||||
],
|
||||
"vision_encoder": [
|
||||
"transformers",
|
||||
"CLIPVisionModelWithProjection"
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"_class_name": "EulerAncestralDiscreteScheduler",
|
||||
"_diffusers_version": "0.24.0",
|
||||
"beta_end": 0.012,
|
||||
"beta_schedule": "linear",
|
||||
"beta_start": 0.00085,
|
||||
"clip_sample": false,
|
||||
"num_train_timesteps": 1000,
|
||||
"prediction_type": "v_prediction",
|
||||
"set_alpha_to_one": false,
|
||||
"skip_prk_steps": true,
|
||||
"steps_offset": 1,
|
||||
"timestep_spacing": "linspace",
|
||||
"trained_betas": null
|
||||
}
|
||||
@@ -0,0 +1,25 @@
|
||||
{
|
||||
"_name_or_path": "D:\\.cache\\huggingface\\hub\\models--sudo-ai--zero123plus-v1.1\\snapshots\\36df7de980afd15f80b2e1a4e9a920d7020e2654\\text_encoder",
|
||||
"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": "float16",
|
||||
"transformers_version": "4.36.0",
|
||||
"vocab_size": 49408
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -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 +1,38 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "!",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"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": true,
|
||||
"do_lower_case": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 77,
|
||||
"pad_token": "!",
|
||||
"tokenizer_class": "CLIPTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,73 @@
|
||||
{
|
||||
"_class_name": "UNet2DConditionModel",
|
||||
"_diffusers_version": "0.24.0",
|
||||
"_name_or_path": "D:\\.cache\\huggingface\\hub\\models--stabilityai--stable-diffusion-2\\snapshots\\1e128c8891e52218b74cde8f26dbfc701cb99d79\\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": 96,
|
||||
"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": false,
|
||||
"use_linear_projection": true
|
||||
}
|
||||
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_class_name": "AutoencoderKL",
|
||||
"_diffusers_version": "0.24.0",
|
||||
"_name_or_path": "D:\\.cache\\huggingface\\hub\\models--sudo-ai--zero123plus-v1.1\\snapshots\\36df7de980afd15f80b2e1a4e9a920d7020e2654\\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,
|
||||
"layers_per_block": 2,
|
||||
"norm_num_groups": 32,
|
||||
"out_channels": 3,
|
||||
"sample_size": 256,
|
||||
"scaling_factor": 0.18215,
|
||||
"up_block_types": [
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D",
|
||||
"UpDecoderBlock2D"
|
||||
]
|
||||
}
|
||||
@@ -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"
|
||||
}
|
||||
Reference in New Issue
Block a user