Upload folder using huggingface_hub

.gitattributes

@@ -25,7 +25,6 @@
 *.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

README.md

@@ -1,3 +1,35 @@
 ---
-license: mit
+tags:
+- Text-to-Video
+license: cc-by-nc-4.0
 ---
+
+![model example](https://i.imgur.com/fosRCN2.png)
+
+# zeroscope_v2 30x448x256
+
+A watermark-free Modelscope-based video model optimized for producing high-quality 16:9 compositions and a smooth video output. This model was trained from the [original weights](https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis) using 9,923 clips and 29,769 tagged frames at 30 frames, 448x256 resolution.<br />
+
+zeroscope_v2 30x448x256 is specifically designed for upscaling with [Potat1](https://huggingface.co/camenduru/potat1) using vid2vid in the [1111 text2video](https://github.com/kabachuha/sd-webui-text2video) extension by [kabachuha](https://github.com/kabachuha). Leveraging this model as a preliminary step allows for superior overall compositions at higher resolutions in Potat1, permitting faster exploration in 448x256 before transitioning to a high-resolution render. See an [example output](https://i.imgur.com/lj90FYP.mp4) that has been upscaled to 1152 x 640 using Potat1.<br />
+
+### Using it with the 1111 text2video extension
+
+1. Rename the file 'zeroscope_v2_30x448x256.pth' to 'text2video_pytorch_model.pth'.
+2. Rename the file 'zeroscope_v2_30x448x256_text.bin' to 'open_clip_pytorch_model.bin'.
+3. Replace the respective files in the 'stable-diffusion-webui\models\ModelScope\t2v' directory.
+
+
+### Upscaling recommendations
+
+For upscaling, it's recommended to use Potat1 via vid2vid in the 1111 extension. Aim for a resolution of 1152x640 and a denoise strength between 0.66 and 0.85. Remember to use the same prompt and settings that were used to generate the original clip.
+
+
+### Known issues
+
+Lower resolutions or fewer frames could lead to suboptimal output. <br />
+Certain clips might appear with cuts. This will be fixed in the upcoming 2.1 version, which will incorporate a cleaner dataset.
+Some clips may playback too slowly, requiring prompt engineering for an increased pace.
+
+
+
+Thanks to [camenduru](https://github.com/camenduru), [kabachuha](https://github.com/kabachuha), [ExponentialML](https://github.com/ExponentialML), [polyware](https://twitter.com/polyware_ai), [tin2tin](https://github.com/tin2tin)<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 sha256:53bd18c6d0fc75208fa47ce2b534ff9878280a6d6867a4108d9160809f3a90a4
+size 680904225

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:cf7b342dd7c5bd979c8836689e24cd1e8aa41a735c41bd4164ac84759e56785c
+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 sha256:7cfdd672df17db3283633acb3721afc7735927293c2d3bd2bf64939a6dcd950e
+size 167407857

zeroscope_v2_30x448x256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f8784148193f58209c9954f324173cf5f6b04d3cada762d0b98b140d5be2bda
+size 2822976729

zeroscope_v2_30x448x256_text.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c4972695e1c8005e929fe9d8e857f2dbd65967900c195eabe5223567a57794
+size 1972454741