Hey everyone, I'm excited to share this latest experimental version of RainbowPatch with you. I know there's still work to be done, but I'm always looking for feedback to help make it even better. If you have a moment, I would really appreciate it if you could share your thoughts in a review. Your feedback means a lot to me and will help shape the future of this project. Thank you!
Here are some prompts examples
Prompt: Portrait of a Beautiful Woman
Negative prompts: non
Prompt: Portrait of a beautiful superhero woman
Negative prompts: non
Prompt: A Portrait of Wonder Woman, a detailed face, (detailed eyes), women
Negative prompt: Logo, watermark, (double faces, merged faces),(poorly drawn),(mutilated), (lowres), (deformed), (CG), (3d), (blurry), (out-of-focus), (depth_of_field), (duplicate), (watermark), (label), (signature), (text), (cropped), bad eyes, (((mutated hands and fingers))), (((out of frame)))
Steps: 30, Sampler: Euler a, CFG scale: 7, Seed: 1670235636, Size: 512x768, Model hash: d9d11a9ff2
You can use the trigger word (Rainbowpatch) if you want. normally it doesn't require you to use that because the style is heavily implemented in the model.
Description
I renamed my model version to improve clarity and consistency. The new name reflects a more accurate and intuitive numbering system, making it easier for users to navigate and understand the different versions.
FAQ
Comments (6)
it look exactly like the images we can generate on lexica
I think Lexicas model is better it's sharper and all the images have a unique darker tone to them.
@Patchmonk You could try merging with https://civitai.com/models/10391/noise-offset-for-true-darkness-in-sd for a darker tone.
@randallaware Thank you for your suggestion, I enjoyed training my models, but for some reason, I never got a good result mixing models.
@Patchmonk i just merged your rainbowpatch model with the model I linked above, with add difference of 1 with base 1.5 SD model as the tertiary model and am getting amazing results. https://imgur.com/a/5HECjGE
@randallaware Wow, your results are really good. hopefully, I will come up with something better in 2.0, thinking about adding a lot of variations to the existing data set. so far didn't get any great results but hopefully, I'll be able to release it soon. and also good luck with your mixing.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.