CHECK THE LINK: TRY MY NEW MODEL!
An experimental model based on the NoobAI-XL Epsilon-pred 1.1-Version.
In this model, I tried to improve the overall characteristics of the model without changing or damaging the style.
Overall, I managed to achieve improvements in consistency, anatomy, and style.
Sampling method: Euler a
Sampling steps: 30
CFG Scale: 4 - 7
Prompt
{prompt}
very awa, masterpiece, best quality, high quality, newest, recent, year 2024, absurdres, Negative prompt (TRY NOT TO USE SUCH A LONG PROMPT, IT'S JUST AN EXAMPLE)
worst aesthetic, good quality, normal quality, low quality, bad quality, worst quality, mid, early, old, lowres, low res, thumbnail, scan artifacts, jpeg artifacts, compression artifacts, lossy-lossless, adversarial noise, ai-generated, ai-assisted, abstract, official art, 4koma, multiple views, reference sheet, dakimakura \(medium\), censored, bar censor, mosaic censoring, turnaround, comic, sketch, unfinished, watermark, logo, signature, text, artist name, dated, username, web address, bad hands, bad feet, extra digits, fewer digits, extra arms, extra faces, multiple heads, missing limb, amputee, severed limb, mutated hands, distorted anatomy, blurry, off-topic, artistic error, bad proportions, bad perspective, bad anatomy, what, meme, tagme, copyright name, copyright symbol, resized, downscaled, source larger, ugly, aliasing, simple background, asymmetrical, concept art, cropped, bleed through, crease, bad aspect ratio, derivative work, MD5 mismatch, moire, third-party edit, image sample, upscaled, Waifu2x, unmoving pattern, third-party watermark, has bad revision, doesnotexist, bkub, Description
FAQ
Comments (6)
Cool model, what artists/concepts did you train on? How many images and for how many epochs?
Sorry for the confusion. I chose the wrong option. It was a merge. 😅
@voider Oh well, it's got cool results, what models or loras do you like to merge?
@SulphAI spo, dpo, a huge pile of detailers, stabilizer and aesthetic enhancement.
If you need more details, write your discord in the dm on site
@SulphAI Although in the second version I unnecessarily added a stabilizer and new reality, which affected the style of the results.
@voider don't worry keep improving it people new updated base models and this one











