For business inquires, commercial licensing, custom models, and consultation contact me under yamer@rundiffusion.com
๐๐ฑ๐ฎ๐ฌ๐ด๐น๐ธ๐ฒ๐ท๐ฝ ๐ฃ๐๐น๐ฎ: ๐๐ท๐ฒ๐ถ๐ฎ/๐๐ธ๐ท๐ฌ๐ฎ๐น๐ฝ/๐๐ฎ๐ท๐ฎ๐ป๐ช๐ต ๐ค๐ผ๐ฎ/๐๐ช๐ท๐ฝ๐ช๐ผ๐ /๐๐ธ๐ถ๐ฒ๐ฌ
Follow me on Twitter: @YamerOfficial --- Discord: yamer_ai
If you have enjoyed thischeckpoint support me on ko-fi: https://ko-fi.com/yamer
Unstable Illustrator รNA is a merged model of Unstable Diffuser V9-VAE, Yamer's Anime V5+VAE, blue_pencil-XL, Anime Illust Diffusion XL, with a bit of tweaking to the training data.
Nsfw is much better, now the model can handle nudity better, the style is similar to Yamer's Anime V5 because it is the main component of the รNA checkpoint, now using the XL_VAE_C E7 VAE that gives an even better saturation to the image. This model is perfect for stylized images, abstract art and anime!
Have fun exploring the vastity of styles and images that you can create ^-^
Yamer's Anime version 1 to 5 is a group of models that is specialized in anime like images, this model is being added in the "Ultra Infinity (now called) Unstable Illustrator" family because it follows the same theme (anime), this checkpoint is not specialized in nsfw content, I recommend to use a LoRA for specific images.
When creating this checkpoint I trained it on anime images in various styles, this model is not completely trained, it is a a trained and merged models, other anime models were used as base to achieve the current style that is unique to this model.
(OLD, SD 1.5!) Ultra Infinity V2 - Yamime is a model that specializes in anime-like images and sharp results, there is no need for trigger words because the model will already give you anime style results, I advice users to not go beyond a CGF scale of 25 because they colors may break and corrupt, please use the model between 7-25 for sharp colorful results that will satisfy your need without destroying the image. This model is a big improvement from the previous version with the new sharp style and a better recognition of anime stylized compositions like bodies, background and objects.
Pฬฝอeฬฝอrฬฝอsฬฝอoฬฝอnฬฝอaฬฝอlฬฝอ ฬฝอRฬฝอaฬฝอtฬฝอiฬฝอnฬฝอgฬฝอ:ฬฝอ
Quality: 9/10
Stability: 7.5/10
Flexibility: 7/10
CFG Resistance: 25/30
Style: 9/10
NSFW: 7.5/10
----------
Creator Note:"If you found the results achieved by this model to be satisfying, I would greatly appreciate it if you could kindly consider leaving a positive review. Your feedback and support are invaluable to me." :3
๐ฝ๐๐๐๐๐ค ๐จ๐๐๐ฃ๐ ๐ฅ๐๐๐ค ๐๐ ๐๐๐ ๐๐ค ๐๐๐ฅ๐ฅ๐๐ฃ ๐ฅ๐๐๐ ๐ฃ๐๐๐ฆ๐๐๐ฃ ๐๐ป๐๐๐.๐:
No embedding needed
Better variety of style
The refiner is not needed
Less AI generated look to the image. (When creating anime or realistic images for example)
No face fix needed
Better saturation, overall quality, texture and tonality
Less blurry images (images look sharper)
No adetailer required (Just use hires fix)
เธ ^โข๏ปโข^เธ Works best using:
Restore Face: It is not needed to generate high quality images (Not used in the current showcase.)
Clip skip: 1-2 (The model works well with clip skip set to both.)
SDXL Refiner: Not used with my models
1) Show em big mommy milkies in my dm. 2) A massive tiddie generates a gravitational field by warping the geometry of the surrounding spacetime. 3) Anime hentai is the highest form of research. -Yamer
๐ฝ๐๐๐๐๐๐๐๐๐๐ ๐๐๐๐๐๐๐๐:
Resolution and steps: 1024x1024
Steps: 30 to 150
CFG: 7 to 25
Hires Upscaler: 4x_foolhardy_Remacri or 4xUltraSharp
----------
Hi, I'm an Italian creator on a mission to spread the joy of using AI to generate images and the progress it has made in the past few years. I craft checkpoints and prompts that anyone can use to generate their own art and share it. My ultimate aim is to be a good creator, sharing the models I create as a hobby with others.