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
It's now more like Anima Preview 2, but it might be a bit unstable
FAQ
Comments (9)
I am not sure why, but I am really struggling to get detailed faces with Anima. I am using SwarmUI and have made sure I have the VAE and T5 enabled, and I'm also using adetailer. No matter what though, the faces severely lack detail.
Anyone else have this issue or know how to fix it?
Try not to use too many quality tags; "Best Quality" is sufficient for most.
@MightyCrimson I only have masterpiece as my quality tag.
@BingusChungus Don't have T5 enabled. I heard it generally makes things worse since the text encoder that comes with the anima model surpasses it. Hope this helps a bit.
Seed variety destroyed. Even with dpmpp_2m_sde different seeds give very similar results. I have a felling that distillation lora was merged without a notice.
While the overall quality is good, v2.7 often breaks with multiple characters on wide aspect ratios (16 by 9, for example).
Also, it's always better to include at least one example image with prompt and all other information.
I notice I cannot use this for Lora training in Kohya. Help...
Please incorporate Anima P3! Thank you again for this model!
P3 came out?!