AniExioMO|M4 - v2b9

AniExioMO|M4

CHECKPOINT
Original


Updated:

__________________________________________________________________________________________

Custom Generation TAB Settings:

🎲 CFG Scale: 4 | 4.5 | 5 | (Optimal)

🧼 Samplers / Schedulers: Euler, Euler A, ER_SDE, DMP_2M_SDE_GPU + SGM_Uniform or BETA (i use "sgm_uniform" now)

👣 Steps: 32 — 40

✨ PROMPT PARAMETERS

✔️ Quality (Anima): masterpiece, best quality or masterpiece, best quality, score_7

(very aesthetic — optional)

❌ Negative (Illustrious+Anima): watermark, signature, copyright name, artist name, logo, text, english text, artist logo, twitter logo, twitter username, character name, patreon name, patreon logo, worst quality, low quality, bad , jpeg artifacts,, sepia, fewer digits, extra digits, bad hands, bad , score_1, score_2, score_3, child, childish

__________________________________________________________________________________________

🎬 ComfyUI - Settings:

📸 CLIP SKIP: 2

🎲 CFG Scale: 4.5 | 5 | 5.5 | 6 (Optimal) / Shift 3.0-3.5 weight

🧼 Samplers / Schedulers: you can choose from er_sde (neutral and sharp), euler_a (softer, slightly more 2.5D), or dpmpp_2m_sde_gpu (more creative but wilder).

Hightly recommended: ER SDE

👣 Steps: 30 — 40

♨️ Hi-Res Fix: 4x-UltraSharp or Foolhardy Remacri (You can not use them, but with them more detailed images)

🎭 Adetailer: Not supported yet, use Upscale Nods.

📐 Recommended Resolution: 896x1152 - 1152x896 or 832x1216 - 1216x832, Simple: 1024x1024

✨ PROMPT PARAMETERS

✔️ Quality (Anima): masterpiece, best quality or masterpiece, best quality, score_7

(very aesthetic — optional)

❌ Negative (Illustrious+Anima): watermark, signature, copyright name, artist name, logo, text, english text, artist logo, twitter logo, twitter username, character name, patreon name, patreon logo, worst quality, low quality, bad , jpeg artifacts,, sepia, fewer digits, extra digits, bad hands, bad , score_1, score_2, score_3

Version Detail

Anima
Here are 2 versions of the model, very briefly on them: v2b9 — A version with vastly improved image quality, containing a minimum of style. This is an experimental model expanded with my personally curated dataset + a newly self-made tool for merging models+LoRA was used, along with special algorithms. The quality of my models should now double. This version is the fruit of all my best developments and the transition to a new improvement model — you should definitely try it.

Project Permissions

Reprinting is strictly prohibited

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts