Unified Style and Subject-Driven Generation with ByteDance’s USO model
Download JSON Workflow
Use the image below as an input image.Load Checkpoint
node has flux1-dev-fp8.safetensors
loadedLoraLoaderModelOnly
node has dit_lora.safetensors
loadedModelPatchLoader
node has projector.safetensors
loadedLoad CLIP Vision
node has sigclip_vision_patch14_384.safetensors
loadedUpload
to upload the input image we providedcontent reference
image input. If you want to use the style reference
image input, you can use Ctrl-B
to bypass the marked node group.Run
button, or use the shortcut Ctrl(Cmd) + Enter
to run the workflowcontent reference
node and only use an Empty Latent Image
node.
Style Reference
group and use the workflow as a text to image workflow, which means this workflow has 4 variations