[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/vt/ - Virtual Youtubers

Search:


View post   

>> No.63723272 [View]
File: 2.68 MB, 1024x1536, ComfyDiff_00034.webm [View same] [iqdb] [saucenao] [google]
63723272

>>63722453
>>63721368
So I can run 4x after image generation just fine, but that would be similar to running it from 'Extras' tab in A1111 which just accentuates the issues.
I would need to create a workflow that extracts the images 1 by 1 instead and does controlnet processing before upscaling them individually with img2img.

Navigation
View posts[+24][+48][+96]