[Improvement] For Case 1 (Standard Use), we've enabled the use of multiple images (turn it OFF if you don't use it). This expands the possibilities, such as changing background images.
Runtime profile
Source description
Release Note
(v1.0 -> v2.0)
[Improvement] For Case 1 (Standard Use), we've enabled the use of multiple images (turn it OFF if you don't use it). This expands the possibilities, such as changing background images.
[Improvement] Added Refiner (SDXL). If you created (image 1) using SDXL, this should help make the generated image quality closer to the original.
Overview
In image editing, I believe Qwen Image Edit holds potential. Therefore, I have “industrialized” four cases that will likely be used frequently: standard use, background extension, impainting, and pose replacement.
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Qwen Image Edit 2511 Factory Version 2 is an image-editing workflow for standard use, background extension, inpainting, and pose replacement. It takes source images, prompts, masks, resolution settings, and pose images, and produces edited images.
Select a mode, then provide the image, prompt, resolution, mask, or pose image required for that mode.
Optional features include a simple Refiner and an Upscaler. If a result is unsatisfactory, correct it with an additional prompt.
Standard use takes a source image in image 1 and a prompt; multiple images can also be used, including for changing backgrounds.
Background extension takes a source image in image 1 and a resolution setting. Inpainting takes a source image in image 1, an edited mask, and a prompt.
Pose change takes the original image in image 1 and a pose image in image 2; HD quality is preferred for the pose image.
It is listed as a Workflows item, uses Qwen as its base model, and is published by Usako USA.
Listed node packs are ComfyUI_Comfyroll_CustomNodes, comfyui_layerstyle, comfyui-custom-scripts, comfyui-kjnodes, ComfyUI-tbox, rgthree-comfy, and was-ns.
Listed model files include qwen_2.5_vl_7b_fp8_scaled.safetensors, qwen_image_edit_2511_bf16.safetensors, qwen_image_vae.safetensors, and Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors.
Additional listed model files are sd_xl_refiner_1.0_0.9vae.safetensors, usako_qwen.safetensors, and vxpXLLCM_vxpXLV10.safetensors.
Standard use supports multiple images for uses such as changing background images; turn the option off when you do not use it.
For inpainting, edit the mask before writing the prompt. For pose change, use DW or Depth for ControlNet.
Before using it, verify that was-ns, sd_xl_refiner_1.0_0.9vae.safetensors, usako_qwen.safetensors, and vxpXLLCM_vxpXLV10.safetensors are available.
Suggestion · not verified
No license information is listed, so verify the usage terms before using it.
Suggestion · not verified
Does this need to be edited?
Sign in to send an edit request.
Sources
1 sourceSource excerpts
1 excerptSource context: 615 downloads · Type Workflows · Base model Qwen
Usage:
First, select a mode.
For Case 1 (Standard Use), simply upload the source image to (image 1) and write your prompt.
For Case 2 (Background Extension), simply upload the source image to (image 1) and set the resolution.
For Case 3 (Inpainting), upload the source image to (image 1), edit the mask (important), then write your prompt. Refer to this WF for prompt examples.
For Case 4 (Pose Change), upload the original image to (image 1) and upload an image for the pose to (image 2) (HD quality is preferred). Use DW or Depth for ControlNet.
If you are not satisfied with the result, please correct it with an additional prompt.
Additionally, we've provided optional features: a simple Refiner and an Upscaler. Use them as needed.
Estimated VRAM requirement
Estimate unavailable
Model file sizes are not complete enough to calculate this requirement yet.
Requirements
14 requirementsText encoder · Hugging Face · Comfy-Org/HunyuanVideo_1.5_repackaged
Possible sources
qwen_image_edit_2511_bf16.safetensors
ConflictCheckpoint · Unknown
Possible sources
VAE · Hugging Face · Comfy-Org/Qwen-Image_ComfyUI
Qwen-Image-Edit-2511-Lightning-4steps-V1.0-bf16.safetensors
File unverifiedLoRA · Hugging Face · lightx2v/Qwen-Image-Edit-2511-Lightning
sd_xl_refiner_1.0_0.9vae.safetensors
Not resolvedVAE · Unknown
usako_qwen.safetensors
Not resolvedLoRA · Unknown
vxpXLLCM_vxpXLV10.safetensors
Not resolvedCheckpoint · Unknown
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
Node pack · Registry
was-ns
Not resolvedNode pack · Registry