bytedance/InfiniteYou
🔥 [ICCV 2025 Highlight] InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
Introduces InfuseNet, a residual-connection-based identity injection component for Diffusion Transformers (DiTs) that preserves facial identity while enabling flexible image generation with improved text-image alignment. The framework employs multi-stage training with synthetic single-person-multiple-sample (SPMS) data to enhance quality and mitigate face copy-pasting artifacts. Offers plug-and-play compatibility with existing methods, integrates with ComfyUI, and provides quantization and CPU offloading options to reduce peak VRAM from 43GB to 16GB without performance degradation.
2,670 stars. No commits in the last 6 months.
Stars
2,670
Forks
286
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bytedance/InfiniteYou"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
River-Zhang/ICEdit
[NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image...
muzishen/IMAGHarmony
🧩 IMAGHarmony 🧩: Controllable image editing with consistent object quantity and layout. A...
AMAP-ML/FE2E
[CVPR 2026] Beyond Generation: Advancing Image Editing Priors for Depth and Normal Estimation
TencentARC/BrushNet
[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting...
ermongroup/SDEdit
PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations