Tensor.Art
Create

RDBT - Anima - reakaakasky - p3 v0.24f dmd2 b

RDBT - Anima - reakaakasky

LORA
Reprint
reakaakasky

Updated:

p3 v0.29.b
p3 v0.24f dmd2 b
p3 v0.24f dmd2
p3 v0.24fd b
p3 v0.24fd (X)
RDBT - Anima - reakaakasky by 😞3 on Tensor.Art

Older versions: https://tensor.art/models/984314389274299629

Update log

[base model version] [finetuned model version] [distillation method] [distillation version]

f = finetuned, cfg = cfg distilled, dmd2 = distribution matching distillation.

N-step dmd2: N means the model can output an image without noise after N steps. It's not a mandatory fixed setting. It's a lower limit. You can always use >N steps. Lower N = stronger distillation.

Recommended versions:

  • p3 v0.24f dmd2 b: 16-step dmd2.

  • p3 v0.24f cfg b: close to vanilla anima.

  • p2 v0.23f dmd2 b: 4-step dmd2. +200% stability

Version Detail

Anima
Latest: (4/14/2026) v0.24f dmd2 b: Comparing with "v0.24f dmd2": Some adjustments in distillation target/loss. Improved details and stability, images should be sharper. Settings about dmd2 weren't changed, still considerably "lower" than normal 8 steps dmd2 (That's why I called this 16 steps dmd2). Cover images are using cfg 1 and 8 steps for demonstration. The model fully converges in ~16 steps. For best quality it is recommended to use cfg 2 and 16 steps. This should be my last update before next anima release. I'm quite happy about the quality, and out of juice and idea. I might try 4 steps dmd2 with fixed style. (Because you can't preserve all styles, why not just amplify a good one, or few.) I'm open for style suggestions. See Update Log section for previous versions. --- Other(Duplicated): https://tensor.art/models/987820381815498088

Project Permissions

Model reprinted from : https://civitai.com/models/2364703

Reprinted models are for communication and learning purposes only, not for commercial use. Original authors can contact us to transfer the models through our Discord channel --- #claim-models.

Related Posts