InfiniteYou is an open-source image-generation and “identity-preserving image editing / generation” framework from ByteDance, designed to generate high-fidelity images that preserve a subject’s identity while allowing flexible editing or re-creation according to textual prompts. Using an architecture built around diffusion transformers (DiTs), InfiniteYou introduces a component called InfuseNet that injects identity features derived from reference images into the generation process — via residual connections — so that the output matches the person’s identity closely, without sacrificing visual quality or text-image alignment. The team uses a multi-stage training strategy with synthetic multi-sample data per identity to fine-tune for both identity consistency and aesthetic quality. Compared to prior methods, InfiniteYou significantly improves on identity similarity, text-prompt adherence, overall image quality, and avoids common problems such as face copy-pasting artifacts.
Features
- Identity-preserving image generation via InfuseNet — ensures output resembles reference person while respecting prompt
- High-fidelity, high-quality image output with strong text-to-image alignment and aesthetic quality
- Multi-stage training (pre-training + supervised finetuning with multi-sample per identity data) for consistency and reliability
- Plug-and-play architecture compatible with other generative tools (control-nets, stylization, adapters) for flexible workflows
- Avoids common artifacts (face copy-pasting, identity drift) often seen in naive image generation approaches
- Open-source: code, pretrained models, and example pipelines available for researchers, artists, and developers
Project Samples
