20251104 update QwenEditUtils 2.2
add Mask option to modify the specific area
https://www.runninghub.ai/post/1985595549766365186?inviteCode=rh-v1279
20251104 update v5.1
add QwenEditAdaptiveLongestEdge to easier adjust longest edge for different image
RH workflow:
QwenEditUtils 2.0 Any Resolution Reference
Experience link:
https://www.runninghub.ai/post/1985595549766365186?inviteCode=rh-v1279
Custom_node:
https://github.com/lrzjason/Comfyui-QwenEditUtils
20251104 update v5.0
20250927 update v4.0
Use with lora https://civarchive.com/models/1939453 v2 for QwenEditPlus Consistence Editing
20250924 update v3.0
Updated plugin for QwenEditPlus
Removed old nodes. The new node should capable old function when disable vl resize.
20250915 update v2.0
Completely solve pixel shift issue.
Use with Consistance Edit Lora, strength: 1 https://civarchive.com/models/1939453/qwenedit-consistance-edit-lora
Use plugin in https://github.com/lrzjason/Comfyui-QwenEditUtils
RH workflow:
QwenEdit Consistance Edit workflow v2.0
Experience link: https://www.runninghub.ai/post/1965033238311915522/?inviteCode=rh-v1279
Kontext like workflow.
Avoid to encode ref image to qwenvl.
Use with Consistance Edit Lora, strength: 0.48 https://civarchive.com/models/1939453/qwenedit-consistance-edit-lora
RH workflow:
It's extremely fun and I highly recommend it to you!
Workflow: QwenEdit Consistance Edit workflow
Experience link: https://www.runninghub.ai/post/1965033238311915522/?inviteCode=rh-v1279
Description
FAQ
Comments (7)
Is there a reason, why resulting image is zoomed in?
This is the model/lora effect not the node.
Hi there, this is not working, thanks
What do you mean not working? Any error?
Hi, i'm trying to change easy clothes and is not working, i tried many ways, prompting, no way,, the pose is not easy but it supposed this should be an easy task....any advice for prompting... following your instructions in the workflow i'm not able to make it work...thanks
@tupu Generally, swaping cloth is based on model abilities. Try to remove the person and only keep the cloth on the reference image which could easier to swap the cloth. The failure wasn't because of the node. It is limited because of the model abilities. The best way to enhance the abilities is to train a try on lora which focused on swapping cloth and it could preserve the details more and easier to achieve the task.
@xiaozhijason Great, really appreciate ur answer, thanks!!