![]() |
|
AI generated fetish images - Printable Version +- Like Ra's Naughty Forum (https://www.likera.com/forum/mybb) +-- Forum: Fetishes, obsessions, traits, features, peculiarities (https://www.likera.com/forum/mybb/Forum-Fetishes-obsessions-traits-features-peculiarities) +--- Forum: Kinky Artificial Intelligence (https://www.likera.com/forum/mybb/Forum-Kinky-Artificial-Intelligence) +---- Forum: Image AI (https://www.likera.com/forum/mybb/Forum-Image-AI) +---- Thread: AI generated fetish images (/Thread-AI-generated-fetish-images) |
RE: AI generated fetish images - spawn - 07 Feb 2026 I thought I would just send an image or two through the new flux2klein4bFp8 model using a text prompt on an existing image and was amazed. The input images were very low quality grey scale bondage images that I downloaded from this site in the magazine area. The images were upscaled, colorized and given a lot more details than the originals had. The only bad thing is that the model does not know what a cloth gag is, but I am sure a lora could be trained with bdsm themed images to fix that. This is much better than any previous ai model worked at this task before. RE: AI generated fetish images - spawn - 11 Feb 2026 (07 Feb 2026, 08:08 )spawn Wrote: I thought I would just send an image or two through the new flux2klein4bFp8 model using a text prompt on an existing image and was amazed. Using this to convert a bunch of old files. Other than the tendency to put heads on backwards it is doing an amazing job stilll. RE: AI generated fetish images - Like Ra - 11 Feb 2026 (07 Feb 2026, 08:08 )spawn Wrote: new flux2klein4bFp8 modelCan we have more details, please? 😇 E.g. about the GUI, prompts, LORAs? RE: AI generated fetish images - d7i - 11 Feb 2026 Very nice results. Can't blame that one with upper body backwards, because that drawing wasn't very detailed and with very unusual position. RE: AI generated fetish images - spawn - 11 Feb 2026 This is all with no loras yet!!! This is just using latest comfy ui with flux2klein4bFp8 workflow. These are the directions I used. I had to update to latest version of everything. https://www.patreon.com/posts/flux-2-klein-for-149436927?utm_campaign=patron_engagement&utm_source=post_link&post_id=149436927&utm_id=0db2311a-5d91-49da-823a-93a8ee2c85fe&utm_medium=email Then I used this link: https://www.patreon.com/file?h=149436927&m=605206778 to download the text image editing workflow. I did have to bypass the Sage patch node and model patch torch settings to make it work. Then I loaded the images into the input directory and went through each image in turn, running it with just the generic "hyper realistic photograph, enhanced, " prompt. Going though a second pass with colorized black and white images to see if that helps informing the ai on the images it is struggling with and will try to customize the prompt to fix errors. |