-
Notifications
You must be signed in to change notification settings - Fork 26.9k
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.
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
[Bug]: Lora cannot be loaded in API mode #7984
Comments
Do you mind sharing your POST payload? |
I got the same warning, lora model was ignored. {
"prompt": "best quality, ultra high res, (photorealistic:1.4), 1girl, brown blazer, black skirt, glasses, thighhighs, ((T shirt)), (upper body), (Kpop idol), (aegyo sal:1), (platinum blonde hair:1), ((puffy eyes)), looking at viewer, facing front, smiling, <lora:koreanDollLikeness_v10:0.66>",
"negative_prompt": "nsfw, paintings, sketches, (worst quality:2), (low quality:2), (normal quality:2), lowres, normal quality, ((monochrome)), ((grayscale)), skin spots, acnes, age spot, glan",
"steps": 28,
"cfg_scale": 8,
"width": 768,
"height": 1024,
"n_iter": 4,
"sampler_index": "DPM++ SDE Karras"
} |
this is my payload, and I can load the lora with webui
|
Is your Superresolution valid? I don't seem to increase the image resolution, even though "Hires upscale": 2. By the way, have you tried the hires.fox of img2img? |
I found this variable stable-diffusion-webui/webui.py Line 203 in 0cc0ee1
I copyed modules.script_callbacks.before_ui_callback() into def api_only(), and works well
|
Yes, it's a bug with the "API" |
after adding this, it works, thank you very much |
works for me, well done! Thanks! |
Thank you bro. it works |
@tenpha I changed it so that I won't go wrong, but it still doesn't work. What about you? |
Im a noob in coding, can you explain where is this "def api_only()" |
it works |
Thank you for your time. But I'm on Collab so can't edit directly, So I downloaded the "webui.py" and edited it locally then reuploaded it in its folder in place of the old file in google drive. But after running SD when I checked, the file was back to the original one and my issue didn't got resolved. It's still showing the error: "Skipping unknown extra network: [loraname_version]". What am I doing wrong? |
Tried this solution to fix the bug for the past few days. Its not working for me |
1 similar comment
Tried this solution to fix the bug for the past few days. Its not working for me |
Thank you. it works |
Yes, this works very well! Thank you |
Edit the webui.py file first, and then you need to restart the process |
It doesn't work in the latest version |
updated today our stack ( [5ab7f21] - latest release 2nd of May 23) and this "patch" is still working fine. for workflow / Docker we are using this little sed patch. |
The fix worked for me |
Why is this still a bug and not fixed in the API >.<? |
Merged in dev. #12387 |
Is there an existing issue for this?
What happened?
when I run webui --api to start a simple api only server, and I post a http request ,it show
Skipping unknown extra network: lora
100%|████████████████████████████████████████████████████████████████████████████████████████████| 40/40 [00:11<00:00, 3.39it/s]
INFO: 127.0.0.1:38420 - "POST /sdapi/v1/txt2img HTTP/1.1" 200 OK
INFO: 127.0.0.1:38647 - "POST /sdapi/v1/png-info HTTP/1.1" 200 OK
And I check the web.py, It seems that lora is not registered,for some reason I can't access the web page, so I don't konw if lora works
Steps to reproduce the problem
What should have happened?
Skipping unknown extra network: lora shouldn't happen
Commit where the problem happens
release v1.0.0-pre
What platforms do you use to access the UI ?
No response
What browsers do you use to access the UI ?
No response
Command Line Arguments
List of extensions
No
Console logs
Additional information
No response
The text was updated successfully, but these errors were encountered: