Duplicate from showlab/show-1-base

Co-authored-by: David Junhao ZHANG <Junhao233@users.noreply.huggingface.co>

.gitattributes

@@ -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

README.md

@@ -0,0 +1,73 @@
+---
+license: cc-by-nc-4.0
+tags: 
+  - text-to-video
+---
+
+# show-1-base
+
+Pixel-based VDMs can generate motion accurately aligned with the textual prompt but typically demand expensive computational costs in terms of time and GPU memory, especially when generating high-resolution videos. Latent-based VDMs are more resource-efficient because they work in a reduced-dimension latent space. But it is challenging for such small latent space (e.g., 64×40 for 256×160 videos) to cover rich yet necessary visual semantic details as described by the textual prompt. 
+
+To marry the strength and alleviate the weakness of pixel-based and latent-based VDMs, we introduce **Show-1**, an efficient text-to-video model that generates videos of not only decent video-text alignment but also high visual quality.
+
+![](https://showlab.github.io/Show-1/assets/images/method.png)
+
+## Model Details
+
+This is the base model of Show-1 that generates videos with 8 keyframes at a resolution of 64x40. The model is finetuned from [DeepFloyd/IF-I-L-v1.0](https://huggingface.co/DeepFloyd/IF-I-L-v1.0) on the [WebVid-10M](https://maxbain.com/webvid-dataset/) and [InternVid](https://huggingface.co/datasets/OpenGVLab/InternVid) dataset.
+
+- **Developed by:** [Show Lab, National University of Singapore](https://sites.google.com/view/showlab/home?authuser=0)
+- **Model type:** pixel- and latent-based cascaded text-to-video diffusion model
+- **Cascade stage:** base (keyframe generation)
+- **Finetuned from model:** [DeepFloyd/IF-I-L-v1.0](https://huggingface.co/DeepFloyd/IF-I-L-v1.0)
+- **License:** Creative Commons Attribution Non Commercial 4.0
+- **Resources for more information:** [GitHub](https://github.com/showlab/Show-1), [Website](https://showlab.github.io/Show-1/), [arXiv](https://arxiv.org/abs/2309.15818)
+
+## Usage
+
+Clone the GitHub repository and install the requirements:
+
+```bash
+git clone https://github.com/showlab/Show-1.git
+pip install -r requirements.txt
+```
+
+Run the following command to generate a video from a text prompt. By default, this will automatically download all the model weights from huggingface. 
+
+```bash
+python run_inference.py
+```
+
+You can also download the weights manually and change the `pretrained_model_path` in `run_inference.py` to run the inference. 
+
+```bash
+git lfs install
+
+# base
+git clone https://huggingface.co/showlab/show-1-base
+# interp
+git clone https://huggingface.co/showlab/show-1-interpolation
+# sr1
+git clone https://huggingface.co/showlab/show-1-sr1
+# sr2
+git clone https://huggingface.co/showlab/show-1-sr2
+
+```
+
+## Citation
+
+If you make use of our work, please cite our paper.
+```bibtex
+@misc{zhang2023show1,
+    title={Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation}, 
+    author={David Junhao Zhang and Jay Zhangjie Wu and Jia-Wei Liu and Rui Zhao and Lingmin Ran and Yuchao Gu and Difei Gao and Mike Zheng Shou},
+    year={2023},
+    eprint={2309.15818},
+    archivePrefix={arXiv},
+    primaryClass={cs.CV}
+}
+```
+
+## Model Card Contact
+
+This model card is maintained by [David Junhao Zhang](https://junhaozhang98.github.io/) and [Jay Zhangjie Wu](https://jayzjwu.github.io/). For any questions, please feel free to contact us or open an issue in the repository.

feature_extractor/preprocessor_config.json

@@ -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
+  }
+}

model_index.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "TextToVideoIFPipeline",
+  "_diffusers_version": "0.19.1",
+  "_name_or_path": "show-1-base",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DPMSolverMultistepScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "T5EncoderModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "T5Tokenizer"
+  ],
+  "unet": [
+    "showone.models.unet_3d_condition",
+    "UNet3DConditionModel"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "DPMSolverMultistepScheduler",
+  "_diffusers_version": "0.19.1",
+  "algorithm_type": "dpmsolver++",
+  "beta_end": 0.02,
+  "beta_schedule": "squaredcos_cap_v2",
+  "beta_start": 0.0001,
+  "clip_sample": true,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.95,
+  "lambda_min_clipped": -5.1,
+  "lower_order_final": true,
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "sample_max_value": 1.5,
+  "solver_order": 2,
+  "solver_type": "midpoint",
+  "steps_offset": 0,
+  "thresholding": true,
+  "timestep_spacing": "linspace",
+  "trained_betas": null,
+  "use_karras_sigmas": false,
+  "variance_type": "fixed_small"
+}

text_encoder/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/mnt/nfs/HDD-30t/models/IF-I-L-v1.0/text_encoder",
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

text_encoder/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2bb149576a5164f6d46963535d5bfd8e169b6d22bf2e31a6126dbc25be5aaac
+size 9452287259

text_encoder/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bff1eff39c04e7d313e5581cf0d8394d25ac277168062b9e43133c399ba058c
+size 9597033414

text_encoder/pytorch_model.bin.index.json

@@ -0,0 +1,227 @@
+{
+  "metadata": {
+    "total_size": 19575627776
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "shared.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

tokenizer/special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

unet/config.json

@@ -0,0 +1,65 @@
+{
+  "_class_name": "UNet3DConditionModel",
+  "_diffusers_version": "0.19.1",
+  "act_fn": "gelu",
+  "addition_embed_type": "text",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 64,
+  "block_out_channels": [
+    320,
+    640,
+    960,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1280,
+  "cross_attention_norm": "group_norm",
+  "down_block_types": [
+    "ResnetDownsampleBlock3D",
+    "SimpleCrossAttnDownBlock3D",
+    "SimpleCrossAttnDownBlock3D",
+    "SimpleCrossAttnDownBlock3D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": 4096,
+  "encoder_hid_dim_type": "text_proj",
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 3,
+  "layers_per_block": 3,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock3DSimpleCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 6,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "scale_shift",
+  "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,
+  "transfromer_in_opt": false,
+  "up_block_types": [
+    "SimpleCrossAttnUpBlock3D",
+    "SimpleCrossAttnUpBlock3D",
+    "SimpleCrossAttnUpBlock3D",
+    "ResnetUpsampleBlock3D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e8b75789dd964d3a51e96a9753359e77cbbc190b1cb83bcf5775ea6374232b
+size 3454235275