Open PawAlldeller opened 3 months ago
scripts/postprocessing_gfpgan.py in line 29: change this: res = Image.blend(pp.image, res, gfpgan_visibility) to this: res = Image.blend(pp.image.convert("RGB"), res, gfpgan_visibility)
scripts/postprocessing_codeformer.py in line 32: change this: res = Image.blend(pp.image, res, codeformer_visibility) to this: res = Image.blend(pp.image.convert("RGB"), res, codeformer_visibility)
scripts/postprocessing_gfpgan.py in line 29: change this: res = Image.blend(pp.image, res, gfpgan_visibility) to this: res = Image.blend(pp.image.convert("RGB"), res, gfpgan_visibility)
scripts/postprocessing_codeformer.py in line 32: change this: res = Image.blend(pp.image, res, codeformer_visibility) to this: res = Image.blend(pp.image.convert("RGB"), res, codeformer_visibility)
Thanks, this helped!
Is this a bug on my system, or will there be a fix in the new updates?
Now updated to the latest version, same story. Will you have to edit each subsequent version manually?
Thanks, this helped!
Is this a bug on my system, or will there be a fix in the new updates?
Now updated to the latest version, same story. Will you have to edit each subsequent version manually?
Apparently, none of the developers care about this problem. I don't know if this will be fixed.
Checklist
What happened?
После обновления версии на 1.9, сломалост восстановление лиц. В пример касается и GFPGAN и CodeFormer:
Error completing request Arguments: ('task(23eulwtbdi5llkk)', 0.0, <PIL.Image.Image image mode=RGBA size=1024x1150 at 0x2891D69F8B0>, None, '', '', True, True, 0.0, 4, 0.0, 512, 512, True, 'None', 'None', 0, True, 0.696, False, 1, 0, False, 0.5, 0.2, False, 0.9, 0.15, 0.5, False, False, 384, 768, 4096, 409600, 'Maximize area', 0.1, False, ['Horizontal'], False, ['Deepbooru']) {} Traceback (most recent call last): File "W:\stablediffusion v2\webui\modules\call_queue.py", line 57, in f res = list(func(*args, kwargs)) File "W:\stablediffusion v2\webui\modules\call_queue.py", line 36, in f res = func(*args, *kwargs) File "W:\stablediffusion v2\webui\modules\postprocessing.py", line 131, in run_postprocessing_webui return run_postprocessing(args, kwargs) File "W:\stablediffusion v2\webui\modules\postprocessing.py", line 71, in run_postprocessing scripts.scripts_postproc.run(initial_pp, args) File "W:\stablediffusion v2\webui\modules\scripts_postprocessing.py", line 198, in run script.process(single_image, **process_args) File "W:\stablediffusion v2\webui\scripts\postprocessing_gfpgan.py", line 29, in process res = Image.blend(pp.image, res, gfpgan_visibility) File "W:\stablediffusion v2\system\python\lib\site-packages\PIL\Image.py", line 3340, in blend return im1._new(core.blend(im1.im, im2.im, alpha)) ValueError: images do not match
Steps to reproduce the problem
What should have happened?
The sensitivity of facial reconstruction should change.
What browsers do you use to access the UI ?
Mozilla Firefox, Google Chrome
Sysinfo
sysinfo-2024-04-15-12-29.json
Console logs
Additional information
Only automatic updates to the latest version to date, version 1.9