zli12321/FFGO-Video-Customization
Video Content Customization Using First Frame
Leverages LoRA adapters fine-tuned on the Wan2.2-I2V-14B image-to-video model to enable precise video generation control through first-frame conditioning and learned transition phrases. Generates high-resolution videos (1280×720, 81 frames) by decomposing input images into segmented RGBA layers combined with backgrounds, allowing fine-grained customization of video content while maintaining temporal consistency. Integrates with ComfyUI workflows and HuggingFace model hub, with inference optimized for H200 GPUs though memory-saving techniques support A100/H100 deployment.
172 stars.
Stars
172
Forks
11
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zli12321/FFGO-Video-Customization"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
ModelTC/LightX2V
Light Image Video Generation Inference Framework
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators