UNO is an open source image generation framework developed by the Byte Jump intelligent creation team, built on the FLUX.1 model. Its core feature is the use of "less to more" generalization to achieve single-subject/multi-subject customized generation, the main technical highlights include:
- Diffusion converter (DiT) technology: Maintain image subject consistency through context generation capabilities
- UnoPE location embedding: Solving the Feature Obfuscation Problem in Multi-Subject Scenarios
- Data Synthesis Process: Optimized method for generating highly consistent training data
The project uses a tiered authorization model:
- Code Library UsageApache 2.0 licensePermission to modify and redistribute
- The model weights were calculated using theCC BY-NC 4.0 licenseThe use is limited to non-commercial purposes only.
- Commercial applications are subject to the original license terms of FLUX.1-dev.
This answer comes from the articleUNO: Support for single-subject and multi-subject customized image generation tools (suitable for e-commerce graphics)The
Related files download url
You need to log in to download this resource. Go to log in
© Download resources copyright belongs to the author; all resources on this site are from the network, for learning purposes only, please support the original version!
May not be reproduced without permission:AI productivity tools " What is the UNO Framework? What are its main technical features and open source licenses?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil