v4
Compatible with ComfyUI and Forge Neo.
For prompting guidelines, please refer to the official Anima model page.
Positive Prompt:
masterpiece, best quality, [safe / sensitive / explicit, uncensored]
Choose one rating tag: safe, sensitive, or explicit.
Negative Prompt:
worst quality, low quality, score_1, score_2, score_3, artist name
Recommended Settings:
Sampling method: Res Multistep
Schedule type: Simple
Sampling steps: 21–24 (22 recommended)
CFG Scale: 2.5–3.5 (3.0 recommended)
Resolution: Up to 1536 × 1536, depending on available VRAM,
Recommended Resolutions: 1024 × 1024, 832 × 1216, 896 × 1152, 1024 × 1344
Low-VRAM Option:
If you have limited VRAM, you may use the community-made INT8 Qwen3 0.6B text encoder. It can reduce memory usage, although it may not improve generation speed. The official text encoder is recommended if you have sufficient VRAM.
Description
Anima Preview2 has been experimentally merged in a small amount.
However, some issues originating from Preview2 remain, such as cases where the head is not rendered properly.
FAQ
Comments (9)
This has been the most stable Anima model for me, even the latest version with preview2 mixed in. Nicely done! I hope more people will give this a try.
I tested models for highres - this model best in terms of working with words in an image.
v2.5 is in my opinion the best model for anime hands down. Tried hundreds of models from all model families, none blew me away like this one did. LOVE IT!
giko, I love U.😭🥰 I say it once again, This is the best checkpoint of our time!!!
- Comment from South Korea.
Actually a nice finetune but it does kill creativity a bit in the name of anatomy stability. Less dynamic posing kind of like Z-image stiffness. But the backgrounds are AMAZING and make far more perspective sense.
I'm so curious what voodoo you poured into this to make it so good. I think i'll be following Animalka well into Anima 1.0.
I lost
the game?
@sneedingonmyligma420 gallons