RDBT [Anima]

RDBT was trained as a LoRA for better training and distribution efficiency. Main model page: https://civitai.com/models/2364703.

This page contains the ckpt version, for convenience.

Cover images are for demonstration purposes only. This model does not provide styles.

File reupload. If you are the fastest dudes who downloaded previous file, please redownload. That file is a testing version.

Turbo (4-step dmd2)

Fast as f*** boiiiii

4-step dmd2, distilled on top of RDBT finetuned model. See the link above.

Settings:

• Sampler: "euler_a" or "euler".

• CFG scale: 1.

• Steps: 4, 8, or 16. Scheduler: simple. Important: training timestamps are fixed. Other inference timestamps might not work.

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

First time doing 4-step dmd2, also first 4-step dmd2 anima model. I don't know what I'm doing and what to expect...

Huge stability improvement, it even can render long text in 4 steps.

If you want to compare, I've trained:

8-step dmd2 https://civitai.red/models/2364703?modelVersionId=2832699

16-step dmd2 https://civitai.red/models/2364703?modelVersionId=2860424

===================

p1 [fp8]:

fp8 anima preview. Uploaded here for convenience.

About fp8 models:

Quantized fp8 models in ComfyUI format. If you GPU supports it (aka. rtx 4000 and later), ComfyUI will use hardware fp8 automatically, which might (blame Nvidia) be faster. More about ComfyUI fp8, see ComfyUI docs TensorCoreFP8Layout.