thanks to Orellius ❤

README.md

@@ -0,0 +1,54 @@
+---
+thumbnail: https://user-images.githubusercontent.com/54370274/243292723-fa703668-a931-41e1-8bcf-19c72203980b.png
+tags:
+- TextTovideo
+- Text2Video
+- text-to-video 
+---
+
+🐣 Please follow me for new updates https://twitter.com/camenduru <br />
+🔥 Please join our discord server https://discord.gg/k5BwmmvJJU
+
+![00041-3056174990](https://github.com/camenduru/Text-To-Video-Finetuning-colab/assets/54370274/fa703668-a931-41e1-8bcf-19c72203980b)
+
+# Potat 1️⃣ 
+First Open-Source 1024x576 Text To Video Model 🥳  
+
+https://huggingface.co/vdo/potat1-5000/tree/main <br />
+https://huggingface.co/vdo/potat1-10000/tree/main = https://huggingface.co/camenduru/potat1 (you are here) <br />
+https://huggingface.co/vdo/potat1-15000/tree/main <br />
+https://huggingface.co/vdo/potat1-20000/tree/main <br />
+https://huggingface.co/vdo/potat1-25000/tree/main <br />
+https://huggingface.co/vdo/potat1-30000/tree/main <br />
+https://huggingface.co/vdo/potat1-35000/tree/main <br />
+https://huggingface.co/vdo/potat1-40000/tree/main <br />
+https://huggingface.co/vdo/potat1-45000/tree/main <br /> 
+https://huggingface.co/vdo/potat1-50000/tree/main <br />
+
+### Info
+Prototype Model <br />
+Trained with https://lambdalabs.com ❤ 1xA100 (40GB) <br />
+2197 clips, 68388 tagged frames ( [salesforce/blip2-opt-6.7b-coco](https://huggingface.co/Salesforce/blip2-opt-6.7b-coco) ) <br />
+train_steps: 10000 <br />
+
+### Dataset & Config
+https://huggingface.co/camenduru/potat1_dataset/tree/main
+
+### Finetuning
+https://github.com/Breakthrough/PySceneDetect <br />
+https://github.com/ExponentialML/Video-BLIP2-Preprocessor <br />
+https://github.com/ExponentialML/Text-To-Video-Finetuning <br />
+https://github.com/camenduru/Text-To-Video-Finetuning-colab <br />
+
+### Base Model
+https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis <br />
+https://www.modelscope.cn/models/damo/text-to-video-synthesis <br />
+
+Thanks to [damo-vilab](https://damo.alibaba.com/) ❤ [ExponentialML](https://github.com/ExponentialML) ❤ [kabachuha](https://github.com/kabachuha) ❤ [@DiffusersLib](https://twitter.com/DiffusersLib) ❤ [@LambdaAPI](https://twitter.com/LambdaAPI) ❤ [@cerspense](https://twitter.com/cerspense) ❤ [@CiaraRowles1](https://twitter.com/CiaraRowles1) ❤ [@p1atdev_art](https://twitter.com/p1atdev_art)  ❤ <br />
+
+Please try it 🐣 <br />
+https://github.com/camenduru/text-to-video-synthesis-colab <br />
+
+<video src="https://user-images.githubusercontent.com/54370274/243275155-97282de4-e1df-49a0-851e-cb8b4b040441.mp4" data-canonical-src="https://user-images.githubusercontent.com/54370274/243275155-97282de4-e1df-49a0-851e-cb8b4b040441.mp4" controls="controls" muted="muted" class="d-block rounded-bottom-2 border-top width-fit" style="max-height:640px; min-height: 200px"></video>
+
+Potat 2️⃣ is in the oven ♨ <br />

model_index.json

@@ -0,0 +1,24 @@
+{
+  "_class_name": "TextToVideoSDPipeline",
+  "_diffusers_version": "0.17.0.dev0",
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet3DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,18 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.17.0.dev0",
+  "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",
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "./models/model_scope_diffusers/",
+  "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": "4.29.2",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
+size 1361674657

tokenizer/special_tokens_map.json

@@ -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
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,34 @@
+{
+  "_class_name": "UNet3DConditionModel",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "./models/model_scope_diffusers/",
+  "act_fn": "silu",
+  "attention_head_dim": 64,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "CrossAttnDownBlock3D",
+    "DownBlock3D"
+  ],
+  "downsample_padding": 1,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 32,
+  "up_block_types": [
+    "UpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D",
+    "CrossAttnUpBlock3D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85708d921aa6203ea28726fbe445f939c4102a5463ed1f63b951c09b7c587b61
+size 2823110385

vae/config.json

@@ -0,0 +1,31 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.17.0.dev0",
+  "_name_or_path": "./models/model_scope_diffusers/",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 512,
+  "scaling_factor": 0.18215,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0d11ff25d00ceaa02f602831d9cfe650509fdc850c0a1bcb2acdfa03bd5d56
+size 167407857