base verions

README.md

@@ -1,3 +1,60 @@
 ---
 license: apache-2.0
+language:
+  - en
+tags:
+- cogvideox
+- video-generation
+- video-to-video
+- controlnet
+- diffusers
 ---
+
+# CogvideoX-5b Controlnet Extention
+
+
+#### (Warning) This is raw version of controlnet. Better version will be published soon.
+
+### How to
+Clone repo 
+```bash
+git clone https://github.com/TheDenk/cogvideox-controlnet.git
+cd cogvideox-controlnet
+```
+  
+Create venv  
+```bash
+python -m venv venv
+source venv/bin/activate
+```
+  
+Install requirements
+```bash
+pip install -r requirements.txt
+```
+
+### Inference examples
+#### Inference with cli
+```bash
+python -m inference.cli_demo \
+    --video_path "resources/car.mp4" \
+    --prompt "The camera follows behind red car. Car is surrounded by a panoramic view of the vast, azure ocean. Seagulls soar overhead, and in the distance, a lighthouse stands sentinel, its beam cutting through the twilight. The scene captures a perfect blend of adventure and serenity, with the car symbolizing freedom on the open sea." \
+    --controlnet_type "canny" \
+    --base_model_path THUDM/CogVideoX-5b \
+    --controlnet_model_path TheDenk/cogvideox-5b-controlnet-canny-v1
+```
+
+#### Inference with Gradio
+```bash
+python -m inference.gradio_web_demo \
+    --controlnet_type "canny" \
+    --base_model_path THUDM/CogVideoX-5b \
+    --controlnet_model_path TheDenk/cogvideox-5b-controlnet-canny-v1
+```
+
+
+## Acknowledgements
+Original code and models [CogVideoX](https://github.com/THUDM/CogVideo/tree/main).  
+
+## Contacts
+<p>Issues should be raised directly in the repository. For professional support and recommendations please <a>[email protected]</a>.</p>

config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "CogVideoXControlnet",
+  "_diffusers_version": "0.31.0.dev0",
+  "activation_fn": "gelu-approximate",
+  "attention_bias": true,
+  "attention_head_dim": 64,
+  "downscale_coef": 8,
+  "dropout": 0.0,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 3,
+  "max_text_seq_length": 226,
+  "norm_elementwise_affine": true,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 30,
+  "num_layers": 12,
+  "out_proj_dim": 3072,
+  "patch_size": 2,
+  "sample_frames": 49,
+  "sample_height": 60,
+  "sample_width": 90,
+  "spatial_interpolation_scale": 1.875,
+  "temporal_compression_ratio": 4,
+  "temporal_interpolation_scale": 1.0,
+  "time_embed_dim": 512,
+  "timestep_activation_fn": "silu",
+  "use_learned_positional_embeddings": false,
+  "use_rotary_positional_embeddings": false,
+  "vae_channels": 16
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab2f0465d31b0a153035f32e18c2d7c9b46413af59227eaea2cca69c8970c572
+size 1506883000