# aigc-apps/VideoX-Fun

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

Repository: https://github.com/aigc-apps/VideoX-Fun
Canonical: https://ross.abutalabs.com/products/videox-fun
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T09:22:24+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 51
- inputs: {"age_days": 723, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2210, forks 187 (observed 2026-08-28T04:06:26.061779+00:00)

## What it is
VideoX-Fun is a Python-based video generation pipeline built on Diffusion Transformer models (CogVideoX-Fun, Wan-Fun) that generates videos at arbitrary resolutions, durations, and FPS from text or images. It also supports training custom baseline and LoRA models for style and control transformations.

## Use cases
- generate videos from text prompts
- create videos from a single image
- train a custom video generation LoRA
- control video generation with canny, depth, or pose conditions
- generate videos at arbitrary resolutions and frame rates
- predict start and end frame video interpolation
- build a talking digital human avatar

## When to choose
- you need flexible-resolution AI video generation with pretrained DiT models
- you want to fine-tune or train your own video generation or LoRA models
- you need controllable video synthesis from conditions like pose or depth

## When to avoid
- you need lightweight real-time video editing rather than generative AI video
- you lack a GPU or cannot afford heavy inference/training compute
- you only need simple video transcoding or cutting

## Facets
- artifact type: library
- maturity: active
- function: video-processing, machine-learning, deep-learning, image-processing
- domain: artificial-intelligence, deep-learning, image-processing
- platform: windows, python
- tags: video-generation, text-to-video, image-to-video, diffusion-transformer, lora-training, cogvideox, wan, aigc, video, linux, gpu

## Member repositories
- aigc-apps/VideoX-Fun (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:26.061779+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:46:06.768172+00:00, confidence not recorded.
  - readme: https://github.com/aigc-apps/VideoX-Fun (fetched 2026-08-28T04:06:26.061779+00:00, sha df4aff8a9ea4)
- Data as of 2026-08-30T08:39:29.467469+00:00.