Key Features

Text-to-image generation.
Instruction-based editing.
Multi-reference conditioning.
Bounding-box layouts.
A 5.6B-parameter model.
Consumer-GPU deployment.
Distilled and undistilled variants.
ComfyUI integration.

Developers can adapt the weights in local pipelines and fine-tune base variants, subject to the model's commercial-license requirements. Core capabilities include Text-to-image generation, Instruction-based editing, Multi-reference conditioning, and Bounding-box layouts.


Public code or model weights are linked from the project, with setup instructions for running or adapting the system. Additional characteristics include A 5.6B-parameter model, Consumer-GPU deployment, Distilled and undistilled variants, and ComfyUI integration.

Get more likes & reach the top of search results by adding this button on your site!

Embed button preview - Light theme
Embed button preview - Dark theme
TurboType Banner

Subscribe to the AI Search Newsletter

Get top updates in AI to your inbox every weekend. It's free!