PKU-YuanGroup/ConsisID
[CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition
This tool helps content creators, marketers, and storytellers generate short videos from a text description while ensuring that the main human subject consistently maintains their identity throughout the clip. You provide a text prompt describing the desired video, and the system outputs a video where the characters look the same from start to finish. It's ideal for anyone needing to create cohesive video content quickly.
835 stars.
Use this if you need to create short, narrative videos from text prompts where the human characters must maintain a consistent appearance, such as for marketing campaigns, educational content, or character-driven storytelling.
Not ideal if you primarily need to generate long, complex videos, or if your main focus is on generating abstract scenes without specific, recurring human subjects.
Stars
835
Forks
44
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PKU-YuanGroup/ConsisID"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
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