MyNiuuu/MOFA-Video
[ECCV 2024] MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model.
This tool helps animators, artists, and content creators bring still images to life by generating motion. You provide a static image and define movement through simple drawing (trajectories) or by setting key points, or even by using an audio file or a reference video to drive facial expressions. The output is a video showing your image in motion, perfect for creating dynamic visual content from a single frame.
767 stars. No commits in the last 6 months.
Use this if you want to animate parts of a still image, such as making a character move, an object glide, or a face express emotions, with precise control over the motion.
Not ideal if you need to generate completely new video content from text or if your primary goal is general video editing or post-production.
Stars
767
Forks
50
Language
Python
License
—
Category
Last pushed
Dec 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MyNiuuu/MOFA-Video"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...