Hope to support JD's new model based on LTX 2.3
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 10h
- Merged PRs (30d)
- 153
Description
### Feature Idea
JD.com is a major tech company in China and recently released a long-video generation model built on LTX 2.3. This model supports generating short videos up to 5 minutes long and introduces the concept of a "Memory Bank." It strictly maintains consistency for characters and scenes using JSON formatting. I've already tested it with third-party software, and the results are excellent. Currently, the model supports Text-to-Video (T2V), and an Image-to-Video (I2V) version will be released soon. I'm hoping to see ComfyUI support for this model.
https://huggingface.co/jdopensource/JoyAI-Echo
https://github.com/jd-opensource/JoyAI-Echo
https://github.com/user-attachments/assets/be5f6449-03d0-483d-bbcc-4e2cbae093cd
### Existing Solutions
_No response_
### Other
_No response_
Contributor guide
Assessment
This issue has not been assessed yet.