Anima Pixel Decoder
A 25M-parameter decoder that reads the last-layer features of the Anima DiT at the final sampling step and writes RGB pixels directly, in place of the VAE decode. The head and its training follow FastFrames' pixel head (a ConvNeXt readout on the diffusion transformer's features).
| File | anima_pixel_head.safetensors (fp32, 95 MB; shape in the file's metadata) |
| Input | the input of the DiT's final_layer.linear (2048-dim per token, after the adaLN-modulated LayerNorm) |
| Output | a 16Γ16 RGB patch per token, in [-1, 1] |
| Architecture | linear projection of the feature + linear embedding of the x_t patch, 2 ConvNeXt, one 2Γ pixel-shuffle upsample, 1 ConvNeXt, linear to 8Γ8Γ3 |
| DiT | anima-base-v1.0 (28 blocks) |
| Target | VAE(xΜ0) of the same forward, xΜ0 = x_t β ΟΒ·v |
Compatibility
Read the head only where it was trained:
- Base DiT: Euler, shift 3, 20 β¦ 50 steps (last-step Ο 0.058 β¦ 0.136), read at CFG 4, Spectrum included (its last step is an actual forward).
- Turbo: the 4-step turbo LoRA of anima-turbo-4step, Euler 4 steps, shift 3, CFG 1 (last-step Ο 0.5).
Benchmark
In ComfyUI
Turbo 4 steps, CFG 1, RTX 5070 Ti, 16 prompts at ~1 MP, one seed
| KSampler + VAE Decode | KSampler + Anima Pixel Decode | |
|---|---|---|
| KSampler | 0.976 s | 0.998 s (with the tap) |
| decode | 151 ms | 7 ms |
| decode peak VRAM above the loaded models | 1.22 GB | 0.21 GB |
| PSNR against VAE Decode | β | 36.9 dB |
| total per image | 1.13 s | 1.00 s (1.12Γ) |
ComfyUI keeps the VAE on the card after its first decode, so the VAE column has no move cost.
In anima_lora
The same turbo setting and prompts through anima_lora's inference.py (compiled DiT blocks);
medians. The VAE column is the usual interactive path: the VAE waits on the CPU and goes to the
card for the decode.
| turbo + VAE | turbo + pixel head | |
|---|---|---|
| DiT sampling | 0.97 s | 0.97 s |
| load VAE | 710 ms | β |
| VAE move to the card and back | 35 ms | β |
| decode | 141 ms | 7 ms |
| decode peak VRAM above the DiT | 1.38 GB | 0.24 GB |
| total per image (DiT + decode) | 1.86 s | 0.98 s |
Samples
Turbo 4 steps, CFG 1, seed 42, 1024Γ1024, in ComfyUI (the workflow above); left VAE Decode,
right Anima Pixel Decode, decoded from the same latent. Prompt: masterpiece, best quality, score_7, safe. An anime girl wearing a black tank-top and denim shorts is standing outdoors. She's holding a rectangular sign out in front of her that reads "ANIMA". She's looking at the viewer with a smile. The background features some trees and blue sky with clouds.; the
monochrome pair adds monochrome, comic after safe. Crops: 384Γ384 at native resolution,
x 192β576, y 512β896.
On the monochrome crop the VAE keeps the screentone dots on the shorts; the head renders them as flat grey (see Known limits).
Held-out reads
Held-out reads during training (dB, colour / mono):
| decode point | colour | mono |
|---|---|---|
| turbo 4 steps | 35.90 | 29.01 |
| base 20 steps | 33.71 | 26.58 |
| base 28 steps | 33.83 | 26.38 |
| base 50 steps | 33.49 | 25.48 |
| base 28 + Spectrum | 34.37 | 26.00 |
Known limits
- Screentone dots are smoothed into soft grey shading; textured regions (screentone, dense hatching) come out about 1 β 2.5 levels darker than the VAE in linear light. The lowest per-image PSNRs are manga pages and sketches (turbo 28.7 β 30.9 dB).
- Speed lines and footnote-size glyphs are slightly soft under zoom.
- One trained head, one seed; no run spread.
Use
- ComfyUI: the ComfyUI-Anima-PixelDecoder
node pack (ComfyUI Manager: "Anima Pixel Decoder"). Put this file in
models/pixel_heads/, add Anima Pixel Head Tap on the MODEL before the KSampler (stock or Spectrum) and decode the sampler's LATENT with Anima Pixel Decode instead of VAE Decode. Run the DiT on the fp32 stream (Anima Adapter Loader,stream = fp32). - anima_lora:
inference.py --decoder pixel_head(make test PIXEL=1,make test-turbo PIXEL=1); the module, loader and feature tap are inlibrary/anima/pixel_head.py.
License
The weights in this repository are a Derivative of Anima and are distributed under the CircleStone Labs Non-Commercial License (see NOTICE.md). Any rights to use them are granted directly by CircleStone Labs LLC under that license.
- The model/weights may only be used for non-commercial purposes. Generated images (Outputs) may be used commercially.
- Anima is itself a Derivative Model of NVIDIA Cosmos-Predict2-2B-Text2Image and is subject to the NVIDIA Open Model License Agreement insofar as it applies to Derivative Models.
- This is not an official CircleStone Labs product and is not endorsed by CircleStone Labs.
Built on NVIDIA Cosmos.
Model tree for sorryhyun/anima-pixel-decoder
Base model
nvidia/Cosmos-Predict2-2B-Text2Image