Skip to content

P2 of qwen edit model. #9412

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 5 commits into from
Aug 19, 2025
Merged

P2 of qwen edit model. #9412

merged 5 commits into from
Aug 19, 2025

Conversation

comfyanonymous
Copy link
Owner

No description provided.

@comfyanonymous comfyanonymous added the Run-CI-Test This is an administrative label to tell the CI to run full automatic testing on this PR now. label Aug 19, 2025
@github-actions GitHub Actions
Copy link

(Automated Bot Message) CI Tests are running, you can view the results at https://ci.comfy.org/?branch=9412%2Fmerge

comfyanonymous and others added 3 commits August 18, 2025 20:29
@comfyanonymous
Fix normal qwen.
5c38f8d
@comfyanonymous
Fix.
2f2eb2b
@comfyanonymous
Make the TextEncodeQwenImageEdit also set the ref latent.
fd569ea 
If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
@comfyanonymous comfyanonymous merged commit 4977f20 into master Aug 19, 2025
7 checks passed
@comfyanonymous comfyanonymous deleted the temp_pr branch August 19, 2025 02:38
AuroJoe pushed a commit to AuroJoe/ComfyUI_Alpha that referenced this pull request Aug 19, 2025
@comfyanonymous
P2 of qwen edit model. (comfyanonymous#9412)
421d914 
* P2 of qwen edit model.

* Typo.

* Fix normal qwen.

* Fix.

* Make the TextEncodeQwenImageEdit also set the ref latent.

If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
AuroJoe pushed a commit to AuroJoe/ComfyUI_Alpha that referenced this pull request Aug 19, 2025
@comfyanonymous
P2 of qwen edit model. (comfyanonymous#9412)
0af47c1 
* P2 of qwen edit model.

* Typo.

* Fix normal qwen.

* Fix.

* Make the TextEncodeQwenImageEdit also set the ref latent.

If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
AuroJoe pushed a commit to AuroJoe/ComfyUI_Alpha that referenced this pull request Aug 19, 2025
@comfyanonymous
P2 of qwen edit model. (comfyanonymous#9412)
52e7cb9 
* P2 of qwen edit model.

* Typo.

* Fix normal qwen.

* Fix.

* Make the TextEncodeQwenImageEdit also set the ref latent.

If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
AuroJoe pushed a commit to AuroJoe/ComfyUI_Alpha that referenced this pull request Aug 19, 2025
@comfyanonymous
P2 of qwen edit model. (comfyanonymous#9412)
1c3dceb 
* P2 of qwen edit model.

* Typo.

* Fix normal qwen.

* Fix.

* Make the TextEncodeQwenImageEdit also set the ref latent.

If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
AuroJoe pushed a commit to AuroJoe/ComfyUI_Alpha that referenced this pull request Aug 19, 2025
@comfyanonymous
P2 of qwen edit model. (comfyanonymous#9412)
a72411c 
* P2 of qwen edit model.

* Typo.

* Fix normal qwen.

* Fix.

* Make the TextEncodeQwenImageEdit also set the ref latent.

If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
@mery-96-new
Copy link

mery-96-new commented Aug 19, 2025 •
edited
Loading

image

I'm getting oom error on second run, and also it's taking much longer to run when using "TextEncodeQwenImageEdit", but I'm able to run it much faster with reference latent node, the only drawback is that the result with reference latent node is just bad.

I just marked the area in code which I think is taking longer and also causing the OOM Error, tho I'm not sure. Please look into it

AuroJoe pushed a commit to AuroJoe/ComfyUI_Alpha that referenced this pull request Aug 19, 2025
@comfyanonymous
P2 of qwen edit model. (comfyanonymous#9412)
2f04f5c 
* P2 of qwen edit model.

* Typo.

* Fix normal qwen.

* Fix.

* Make the TextEncodeQwenImageEdit also set the ref latent.

If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
Vander-Bilt pushed a commit to Vander-Bilt/ComfyUI that referenced this pull request Aug 26, 2025
@comfyanonymous
P2 of qwen edit model. (comfyanonymous#9412)
a57e84d 
* P2 of qwen edit model.

* Typo.

* Fix normal qwen.

* Fix.

* Make the TextEncodeQwenImageEdit also set the ref latent.

If you don't want it to set the ref latent and want to use the
ReferenceLatent node with your custom latent instead just disconnect the
VAE.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@yoland68 yoland68 Awaiting requested review from yoland68 yoland68 is a code owner

@robinjhuang robinjhuang Awaiting requested review from robinjhuang robinjhuang is a code owner

@pythongosssss pythongosssss Awaiting requested review from pythongosssss pythongosssss is a code owner

@ltdrdata ltdrdata Awaiting requested review from ltdrdata ltdrdata is a code owner

@Kosinkadink Kosinkadink Awaiting requested review from Kosinkadink Kosinkadink is a code owner

@webfiltered webfiltered Awaiting requested review from webfiltered webfiltered is a code owner

@christian-byrne christian-byrne Awaiting requested review from christian-byrne christian-byrne is a code owner

@guill guill Awaiting requested review from guill guill is a code owner

Assignees
No one assigned
Labels
Run-CI-Test This is an administrative label to tell the CI to run full automatic testing on this PR now.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@comfyanonymous @mery-96-new