Downloads · 30 days
0
svjack/ToonCrafter_with_SketchGuidance_fp16
ToonCrafter_with_SketchGuidance_fp16 is a machine learning model from svjack. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository is an implementation that recreates the SketchGuidance feature of "ToonCrafter".
Downloads · 30 days
0
Access
Public
Updated Dec 7, 2024
Repo size
1 MB
Likes
2
Public
Click a slice to open those files.
.gif7.1 MB · 51%
From the Hugging Face model README
This repository is an implementation that recreates the SketchGuidance feature of "ToonCrafter".
https://github.com/user-attachments/assets/f72f287d-f848-4982-8f91-43c49d037007
This repository contains the ToonCrafter model with additional sketch guidance functionality. The model is hosted on GitHub and can be accessed via the following link:
To clone the repository and set up the environment, follow these steps:
git clone https://github.com/svjack/ToonCrafter_with_SketchGuidance && cd ToonCrafter_with_SketchGuidance
pip install -r requirements.txt
pip install --upgrade einops
pip install pyav==13.1.0
After cloning the repository, you can list the control models available:
ls control_models
Download the sketch_encoder.ckpt file from the Hugging Face repository:
wget https://huggingface.co/Doubiiu/ToonCrafter/resolve/main/sketch_encoder.ckpt
Move the downloaded sketch_encoder.ckpt file to the control_models directory:
cp sketch_encoder.ckpt control_models
Once the repository is cloned and the necessary files are in place, you can run the Gradio app using the following command:
python gradio_app.py
This will start the Gradio interface, allowing you to interact with the ToonCrafter model with sketch guidance.
| Model | Resolution | GPU Mem. & Inference Time (A100, ddim 50steps) | Checkpoint |
|---|---|---|---|
| ToonCrafter_512 | 320x512 | TBD (perframe_ae=True) | Hugging Face |
| SketchEncoder | TBD | TBD | Hugging Face |
Currently, ToonCrafter can support generating videos of up to 16 frames with a resolution of 512x320. The inference time can be reduced by using fewer DDIM steps.
conda create -n tooncrafter python=3.8.5
conda activate tooncrafter
pip install -r requirements.txt
python gradio_app.py