Loading
Have a ComfyUI workflow? Get a readable Workflow Doc in your browser.Make a workflow readable.Try it now ↗
This workflow will bring very significant speed improvements with minimal changes to generation quality.
Runtime profile
Source description
Svdq_Cache-dit_QIE-2509 (Nunchaku+Cache-dit_Qwen-Image-Edit-2509)
This workflow will bring very significant speed improvements with minimal changes to generation quality.
1.Install the nodes in the workflow.
2.Run the wheel install node.
3.Download the models.
4.Update ComfyUI.
5.Enjoy!
Qwen-Image-Edit-2509_Multi-input_maskarea_controlnet:
This workflow is a bit late to the party. There are already tons of great 2509 workflows out there. But if you're still struggling to pick one, then you absolutely have to save this one! It's super easy to use and has all the features you need.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
This workflow edits Qwen Image Edit 2509 images from up to three image inputs, supports masks and ControlNet, and includes nodes to preview and save image results.
PreviewImage and SaveImage nodes provide ways to view and save results; the description does not specify an output file format.
Setup notes say to install the workflow nodes, run the wheel install node, download the models, and update ComfyUI.
The named node packs are ComfyUI-nunchaku, comfyui-easy-use, and ComfyUI-QwenImageLoraLoader.
The workflow also lists comfyui_controlnet_aux and was-ns as node packs.
Named model files are qwen_2.5_vl_fp16.safetensors, svdq-int4_r128-qwen-image-edit-2509-lightningv2.0-4steps.safetensors, and ae.safetensors.
Choose between safetensors and GGUF formats.
Set the resolution manually or use an input image’s resolution.
Before setup, check whether comfyui_controlnet_aux and was-ns are available in your ComfyUI environment.
Suggestion · not verified
The description claims significant speed improvements with minimal changes to generation quality; check both in your own runs before relying on that claim.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
3 excerptsSource context: 1322 downloads · Type Workflows · Base model Qwen
You can quickly switch between safetensors, GGUF.
It supports three images at once for input.
It supports masks and ControlNet.
You can quickly switch between manually entering the resolution or just using the image's resolution.
Qwen-image-edit:
etc.
Remaining hardware or download-size estimates are not available yet.
Requirements
VAE · Hugging Face · Comfy-Org/Lumina_Image_2.0_Repackaged · Lumina Image 2.0 Repackaged
Text encoder · Hugging Face · Comfy-Org/Omnigen2_ComfyUI_repackaged
Source context: 1231 downloads · Type Workflows · Base model Qwen
Source context: 1214 downloads · Type Workflows · Base model Qwen
Checkpoint · 11.8 GB · Hugging Face · nunchaku-ai/nunchaku-qwen-image-edit-2509
comfyui_controlnet_aux
PossibleNode pack · Registry
comfyui-easy-use
FoundNode pack · Registry
Node pack · Registry
ComfyUI-QwenImageLoraLoader
FoundNode pack · Registry
was-ns
Not resolvedNode pack · Registry
