https://github.com/stepfun-ai/ComfyUI-StepVideo
https://github.com/stepfun-ai/ComfyUI-StepVideo
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/stepfun-ai/ComfyUI-StepVideo
- Owner: stepfun-ai
- License: mit
- Created: 2025-03-11T04:12:38.000Z (4 months ago)
- Default Branch: main
- Last Pushed: 2025-03-27T07:52:26.000Z (3 months ago)
- Last Synced: 2025-03-27T08:33:25.300Z (3 months ago)
- Language: Python
- Size: 6.97 MB
- Stars: 30
- Watchers: 2
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-comfyui - **ComfyUI-StepVideo**
- StarryDivineSky - stepfun-ai/ComfyUI-StepVideo - StepVideo 是一个 ComfyUI 的自定义节点集合，专注于视频处理，特别是通过帧插值技术来提升视频质量和帧率。它集成了多种帧插值模型，如 RIFE、DAIN、FILM、EMA-VFI 和 CAIN，允许用户在 ComfyUI 工作流中轻松实现视频帧率倍增。该项目还支持使用不同的插值模型进行混合插值，以达到更好的效果。StepVideo 允许用户自定义插值帧数，控制插值质量，并提供多种优化选项，例如平滑运动和减少伪影。其工作原理是分析视频帧之间的运动信息，然后使用相应的插值模型生成中间帧，从而创建更流畅的视频。此外，该项目还支持修复插帧后可能出现的瑕疵。用户可以通过简单的节点连接和参数调整，快速实现高质量的视频插值，提升视频观看体验。它还包含一些实用的工具节点，方便视频处理流程。总之，ComfyUI-StepVideo 提供了一个强大且灵活的视频帧插值解决方案，适用于各种视频处理任务。 (视频生成_补帧_摘要 / 资源传输下载)
README
# ComfyUI-StepVideo
This repository contains ComfyUI custom nodes for StepVideo.
## TI2V
### Workflow
[TI2V.json](workflow/TI2V.json)
### Model Weights
Download the model weights from [this link](https://huggingface.co/stepfun-ai/stepvideo-ti2v).
### Install
1. Install [Step-Video-TI2V](https://github.com/stepfun-ai/Step-Video-TI2V)
2. Install ComfyUI custom nodes for StepVideo
```bash
cd ComfyUI/custom_nodes
git clone https://github.com/stepfun-ai/ComfyUI-StepVideo.git
```
### Inference
1. Launch Step-Video-TI2V remote_server
```bash
cd Step-Video-TI2V
python api/call_remote_server.py --model_dir where_you_download_dir & ## We assume you have more than 4 GPUs available. This command will return the URL for both the caption API and the VAE API. Please use the returned URL as "remote_server_url" parameter in the "TI2V" node.
```
2. Launch ComfyUI
```bash
cd ComfyUI
python main.py
```
## TI2V_API
### Workflow
[TI2V_API.json](workflow/TI2V_API.json)
### Usage
api_url: https://api.stepfun.com/v1/video/generations
api_key: get api_key from https://platform.stepfun.com
## Todo
- [x] TI2V node
- [x] TI2V_API node
- [ ] T2V node
- [ ] T2V_API node