ToTheBeginning-ComfyUI-DreamO/README.md

DreamO Comfyui

DreamO ComfyUI native implementation.

Important

2025.05.30 - This is a preview release. As we're not deeply familiar with ComfyUI, the implementation may not be optimal and could differ from the original Diffusers version. Contributions from ComfyUI experts to refine the code are welcome.

Install

This implementation is based on the 2025.5.19 version of ComfyUI (commit ID: e930a38). Compatibility issues may occur if you're using an older version.

# manual install
cd custom_nodes
git clone https://github.com/ToTheBeginning/ComfyUI-DreamO.git
# Please make sure that you have installed the forked version of facexlib, not the original facexlib. Otherwise, you may encounter face parsing errors.
pip install -r requirements.txt
# restart comfyui

Models

FLUX models

If your machine already has FLUX models downloaded, you can skip this.

• Original bf16 model: dit, t5
• 8 bit FP8: dit, t5
• Clip and VAE (for all models): clip, vae

DreamO models

• Download all files ending with .safetensors in https://huggingface.co/ByteDance/DreamO/tree/main/comfyui => ComfyUI/models/loras.
• (Support auto-download) Download dreamo-embedding => ComfyUI/models/dreamo
• (Support auto-download) Download ben2 => ComfyUI/models/dreamo
• Download flux-turbo => ComfyUI/models/loras, and rename it to flux-turbo.safetensors

Workflows

We provide two simple workflows in the workflows folder: one for single-condition input and another for multi-condition input. You can refer to https://github.com/bytedance/DreamO?tab=readme-ov-file#supported-tasks to learn more about the tasks supported by DreamO and the expected prompt format.

Nodes

• DreamOProcessorLoader
  • This node loads two image preprocessing models: the BEN2 model for background removal and the facexlib model for aligned face detection.
• DreamORefEncode
  • This node encodes the reference image into a latent representation based on the selected task type. Three task types are available: ip, id, and style.
    • ip: will remove the backgound of the reference image
    • id: will align&crop the face from the reference image, similar to PuLID
    • style: will keep the backgound of the reference image. you still need trigger meta prompt to activate the style transfer task
• ApplyDreamO
  • This node adds a hook to the Flux model to support concatenating the reference latent with the noisy latent.

Note

• The current code does not implement the logic for true CFG, which means you need to set cfg=1 in the sampler node
• As mentioned earlier, we're new to ComfyUI. If you have better workflows or suggestions, please let us know.

Contributions are welcome!

Acknowledgement

The implementation of the ComfyUI plugin refers to ComfyUI_PuLID_Flux_ll.

Future Plans

Please follow our base repository DreamO — we will be releasing an update to the model in the coming weeks.

📧 Contact

If you have any comments or questions, please open a new issue or contact Yanze Wu and Chong Mou.