LightX2V
LightX2V copied to clipboard
ModelTC
Light Video Generation Inference Framework
Has anyone been able to successfully achieve multi-GPU parallelism using the wan2.2 4-step distillation model? I've tested it and the results were very poor. I'm not sure if it's a...
Hello LightX2V contributers, we would like to inquire if you have any plans to add support for AMD GPUs (e.g., MI300x, MI35x). If not, we plan to add support for...
## Title Qwen Image FP8 Offload Crash: `infer_block()` Unexpected Keyword Argument `temb` on RTX 5090 (main branch) --- ### Description When enabling **offload** in `examples/qwen_image/qwen_2511_fp8.py` and running the Qwen Image...
The Kandinsky 5 Pro/Light T2V models look really good. It would be amazing to have a distilled version of the models and loras from you. Thank you so much for...
Hey team, thanks for all the amazing releases. Are you going to work on step distill model for Kandinsky 5? its getting native support later. thanks once again.
./scripts/hunyuan_video_15/run_hy15_i2v_720p.sh =============================================================================== LightX2V Base Environment Variables Summary: ------------------------------------------------------------------------------- lightx2v_path: /root/autodl-tmp/LightX2V model_path: /root/autodl-tmp/HunyuanVideo-1.5/ckpts ------------------------------------------------------------------------------- Model Inference Data Type: BF16 Sensitive Layer Data Type: None Performance Profiling Debug Level: 2 =============================================================================== 2025-12-02...
