SDXL

noobzzz / iL

noobzzz / iL - AI Model cover image
Caricato su
7 feb 2025, 12:52
Utilizzi
475
Recensioni
Eccellente  (1)
Passaggi di campionamento

30

Metodo di campionamento

Euler a

Scala CFG

5

Negativo

text, worst quality, low quality, source filmmaker, 3d,[|ai-generated, ai-assisted, stable diffusion, nai diffusion, worst quality, worst aesthetic, bad quality, normal quality, average quality, oldest, old, early, very displeasing, displeasing, adversarial noise, unknown artist, banned artist, what, off-topic, artist request, text, artist name, signature, username, logo, watermark, copyright name, copyright symbol, resized, downscaled, source larger, low quality, lowres, jpeg artifacts, compression artifacts, blurry, artistic error, bad anatomy, bad hands, bad feet, disfigured, deformed, extra digits, fewer digits, missing fingers, censored, bar censor, mosaic censoring, missing, extra, fewer, bad, hyper, error, ugly, worst, tagme, unfinished, bad proportions, bad perspective, aliasing, simple background, asymmetrical, monochrome, sketch, concept art, flat color, flat colors, simple shading, jaggy lines, traditional media \(artwork\), microsoft paint \(artwork\), ms paint \(medium\), unclear, photo, icon, multiple views, sequence, comic, 2koma, 4koma, multiple images, turnaround, collage, panel skew, letterboxed, framed, border, speech bubble, 3d, lossy-lossless, scan artifacts, out of frame, cropped, [abstract], [doesnotexist]| worst quality, low quality, lowres, jpeg artifacts, bad quality, unfinished, missing, extra, fewer, bad, hyper, error, bad anatomy, bad hands, bad feet, disfigured, deformed, extra digits, fewer digits, missing fingers],

Permessi
  • Allow image generation & sharing
  • Permettete agli utenti di scaricare il vostro modello
  • Usi commerciali

Descrizione

yo here's my attempt at a merge.the main thing here is better colors, similar to vpred. composition and default style are also improved. this is not a v-prediction model as i find current v-prediction noob difficult to use.using multiple quality tags can be unstable. it is kind of biased towards lots of shading. some styles are less pronounced due to the added training of respective models.additional styles added: https://files.catbox.moe/h8gjyv.txtlist of checkpoints usedikastrious v8.1wai-nsfw-illustrious v9.0miaomiaoharem v1.5alist of loras usedstabilizer nb_ep11 v0.58ai styles dump eps1.1 v5ma1ma1helmes v1.0thanks to all authors.

Commenti

Artwork made by noobzzz / iL

1