Heads up: statuses are automated heuristics from commit dates, registry metadata and issue titles. "Stale" can mean "finished and stable"; "Error spike" means error-titled issues are unusually high for that pack lately — worth checking recent issues, not a verdict that it is broken. Always check the repo.

VideoX-Fun Active

VideoX-Fun is a video generation pipeline that can be used to generate AI images and videos, as well as to train baseline and Lora models for Diffusion Transformer. We support direct prediction from pre-trained baseline models to generate videos with different resolutions, durations, and FPS. Additionally, we also support users in training their own baseline and Lora models to perform specific sty

Why: last commit 5 days ago

Repo	aigc-apps/VideoX-Fun (default branch main)
Registry	videox-fun · publisher bubbliiiing · latest 1.0.1 (2026-01-20) · in Manager list: yes
Popularity	rank #286 · 39,801 downloads · 2302 stars
Tags	Video LoRA management Loaders, quantization & speed Wan Qwen-Image
Star velocity	collecting (nightly snapshots started 2026-10-19)
Error issues	1 error-titled issues opened in last 30 days (open+closed) · 2.51 per 100K downloads · baseline 0.17/month over prior 6 months (1 total) · 1.0× baseline (Error spike needs ≥3, ≥2× baseline, ≥0.5 per 100K)
Last commit	2026-10-14 (5 days ago)
Open issues	85+ issues, 15 PRs (fetched 2026-10-19)
pyproject.toml	present · version 1.0.1 · requires-comfyui — · frontend — · requires-python — · 26 deps
Registry ComfyUI req.

Error-titled issues, last 30 days

minimax-h3 train error 2026-09-23 · closed

Open issues mentioning errors / breakage

#293 Shape Error in Wan2.2-Fun-5B-Control-Camera 2025-08-22
#232 Error when convert text_encoder to FSDP in multi gpus 2025-06-25
#195 Using WanFunInpaintPipeline generating video system crash and rebooting 2025-05-01
#187 Error when trying to merge a lora into pipeline with wan2.1_fun/predict_v2v_control.py 2025-04-28
#164 🐛 Bug Report: Error running wan2.1 — ui() missing required positional arguments 2025-04-10
#134 lora_cache broken in current ComfyUI node pack 2025-03-27

Recent commits

2026-10-14 [main] fix(z-image): strip the ComfyUI `model.diffusion_model.` key prefix before converting (#522)
2026-09-29 [main] Upgrade GPU Memory Mode architecture (#521)
2026-09-27 [main] Fix a typo in xFuserLongContextAttention (#520)
2026-09-24 [main] Update Qwen Image 2.1 Control and Flex Forcing (#519)
2026-09-22 [main] Update Readme (#517)