Mini toolsDreamActor-M1
By Grisoon
The project presents a DiT-based animation pipeline with hybrid guidance aimed at holistic controllability (portrait to full-body), multi-scale adaptability, and long-term temporal coherence, producing temporally consistent, identity-preserved human animation.
Multimodal
Overview
DreamActor-M1 is a diffusion-transformer-based human image animation framework that turns a reference image into expressive, identity-preserving human motion video.
Last updated: April 6, 2026
