- Subject-Driven: Place subjects into new scenes while maintaining identity consistency
- Style-Driven: Apply artistic styles to new content based on reference images
- Combined: Use both subject and style references simultaneously
ByteDance USO ComfyUI Native Workflow
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates.
If you can’t find them in the template, your ComfyUI may be outdated.(Desktop version’s update will delay sometime)If nodes are missing when loading a workflow, possible reasons:
- You are not using the latest ComfyUI version(Nightly version)
- You are using Stable or Desktop version (Latest changes may not be included)
- Some nodes failed to import at startup
1. Workflow and input
Download the image below and drag it into ComfyUI to load the corresponding workflow.
Download JSON Workflow
Use the image below as an input image.
2. Model links
checkpoints loras model_patches clip_visions Please download all models and place them in the following directories:3. Workflow instructions

- Load models:
- 1.1 Ensure the
Load Checkpoint
node hasflux1-dev-fp8.safetensors
loaded - 1.2 Ensure the
LoraLoaderModelOnly
node hasdit_lora.safetensors
loaded - 1.3 Ensure the
ModelPatchLoader
node hasprojector.safetensors
loaded - 1.4 Ensure the
Load CLIP Vision
node hassigclip_vision_patch14_384.safetensors
loaded
- 1.1 Ensure the
- Content Reference:
- 2.1 Click
Upload
to upload the input image we provided - 2.2 The
ImageScaleToMaxDimension
node will scale your input image for content reference, 512px will keep more character features, but if you only use the character’s head as input, the final output image often has issues like the character taking up too much space. Setting it to 1024px gives much better results.
- 2.1 Click
- In the example, we only use the
content reference
image input. If you want to use thestyle reference
image input, you can useCtrl-B
to bypass the marked node group. - Write your prompt or keep default
- Set the image size if you need
- The EasyCache node is for inference acceleration, but it will also sacrifice some quality and details. You can bypass it (Ctrl+B) if you don’t need to use it.
- Click the
Run
button, or use the shortcutCtrl(Cmd) + Enter
to run the workflow
4. Additional Notes
- Style reference only:

content reference
node and only use an Empty Latent Image
node.
- You can also bypass whole
Style Reference
group and use the workflow as a text to image workflow, which means this workflow has 4 variations
- Only use content (subject) reference
- Only use style reference
- Mixed content and style reference
- As a text to image workflow