Typemovie's EditIDv2 ensures character identity consistency in complex text-to-image generation, using minimal data for enhanced semantic editing, as shown in IBench tests.
Repositories
typemovie repositories
typemovie/EditIDv2Python
(6 stars) (1 fork) (0 indexed issues) (0 open good first issues)
typemovie/IBenchPython
Image evaluation system in Editid (https://arxiv.org/abs/2503.12526)
(1 star) (1 fork) (0 indexed issues) (0 open good first issues)
TypeMovie-ParaAttention is an enhanced version of ParaAttention, designed to accelerate Diffusion Transformer (DiT) model inference with context parallelism, dynamic caching, and a new high-performance SageAttention backend
(5 stars) (1 fork) (0 indexed issues) (0 open good first issues)
typemovie/TypemovieInferPython
统一的消费级显卡多GPU推理框架 - 支持图像生成(flux/kontext/qwen image/qwen image edit)、视频生成(wan).
(2 stars) (1 fork) (0 indexed issues) (0 open good first issues)