README.md

---
license: other
license_name: circlestone-labs-non-commercial-license
base_model:
- circlestone-labs/Anima
library_name: diffusers
tags:
- diffusers
- safetensors
- sdnq
- transformer-component
- anima
- cosmos
- text-to-image
- uint4
- 4bit
---

# Anima Preview 3 SDNQ UINT4 Transformer Component

4-bit uint4 static SDNQ quantization of the Anima Preview 3 diffusion transformer component from `circlestone-labs/Anima` (`split_files/diffusion_models/anima-preview3-base.safetensors`). This repo is the smallest transformer component and lowest VRAM option in the companion full-pipeline benchmark.

This is a **Diffusers transformer component repo**, not a standalone text-to-image pipeline and not a ComfyUI-native single-file checkpoint. It contains `config.json`, SDNQ quantized safetensors shards, and `quantization_config.json` for `diffusers.CosmosTransformer3DModel`.

For a runnable full Diffusers pipeline with Anima's text encoder, VAE, custom `pipeline.py`, and `llm_adapter`, use the companion repo: [`WaveCut/Anima-Preview-3-SDNQ-uint4-diffusers`](https://huggingface.co/WaveCut/Anima-Preview-3-SDNQ-uint4-diffusers).

## Component Load Test

```python
import torch
import sdnq
from diffusers import CosmosTransformer3DModel

transformer = CosmosTransformer3DModel.from_pretrained(
    "WaveCut/Anima-Preview-3-SDNQ-uint4",
    torch_dtype=torch.bfloat16,
).to("cuda")
```

Component-only smoke test on RTX 5090 32GB:

| Component | Size | Load time | VRAM after load | Peak VRAM while loading |
| --- | ---: | ---: | ---: | ---: |
| Original Anima Preview 3 diffusion model | 3.89 GiB | not measured here | not measured here | not measured here |
| SDNQ UINT4 component | 1.06 GiB (-72.8%) | 2.20s | 1611 MiB | 1611 MiB |
| SDNQ INT8 component | 1.85 GiB (-52.6%) | 12.18s | 2437 MiB | 2437 MiB |

Raw component load data: [`benchmarks/component_load_tests.json`](benchmarks/component_load_tests.json).

## ComfyUI Test

Native original Anima ComfyUI baseline was verified with ComfyUI commit `8505abf52e42f4441d9d53baf4c31a2ec7123400` using:

- `UNETLoader`: `anima-preview3-base.safetensors`
- `CLIPLoader`: `qwen_3_06b_base.safetensors`
- `VAELoader`: `qwen_image_vae.safetensors`
- `ModelSamplingAuraFlow`: shift `3.0`
- `KSampler`: `er_sde`, `simple`, 24 steps, CFG 4.0
- Resolution: `1024x1024`

Original ComfyUI baseline on the same five prompt/seed pairs: mean `6.53s/img`, peak generation VRAM `26519 MiB`. ComfyUI keeps the model mostly lazy/offloaded after loader nodes, so the meaningful memory number is the generation peak. Raw data: [`benchmarks/comfy_original_baseline_1024.json`](benchmarks/comfy_original_baseline_1024.json).

Direct ComfyUI loading of this component repo was also tested through `comfyui-sdnq`'s `SDNQSampler` custom path. It is **not directly loadable** there because that node expects a full Diffusers pipeline directory with `model_index.json`; this repo is only the transformer component. ComfyUI core `UNETLoader` also expects a single diffusion model file and Anima detection requires `llm_adapter.*` weights, which are not present in this component repo. Test log: [`benchmarks/comfy_direct_load_tests.json`](benchmarks/comfy_direct_load_tests.json).

## Full-Pipeline Generation Benchmark

The generation benchmark below uses the companion full Diffusers checkpoints, where these transformer components are combined with Anima's original Qwen3 text encoder, VAE, and learned LLM adapter. This is the runnable comparison against the original full BF16 Diffusers conversion.

![Anima Original BF16 vs SDNQ UINT4 and INT8 1024x1024 grid](images/anima_original_uint4_int8_grid_5x3_1024x1024_1to1.jpg)

The source JPEG is `3572x5576`; every generated cell is exactly `1024x1024` and pasted 1:1 with no resizing. Five prompt/seed pairs are listed in the grid's left column. Raw benchmark JSON: [`benchmarks/full_diffusers_benchmark_results_1024.json`](benchmarks/full_diffusers_benchmark_results_1024.json).

Measured on RTX 5090 32GB with `torch 2.8.0+cu128`, `diffusers 0.38.0`, `transformers 5.8.1`, `sdnq 0.1.8`, `torch.bfloat16`, 24 steps, CFG 4.0, and 1024x1024 output. Network download excluded; one warm-up image discarded; VRAM sampled with `nvidia-smi` every 50 ms.

| Model | Repo | Size | Load time | Mean generation | Speed vs original | VRAM after load | Peak VRAM while generating |
| --- | --- | ---: | ---: | ---: | ---: | ---: | ---: |
| Original BF16 | `CalamitousFelicitousness/Anima-Preview-3-sdnext-diffusers` | 5.3 GiB | 10.04s | 6.37s/img | 1.00x | 6005 MiB | 10759 MiB |
| SDNQ UINT4 full pipeline | `WaveCut/Anima-Preview-3-SDNQ-uint4-diffusers` | 2.7 GiB (-49.1%) | 11.96s | 6.13s/img | 1.04x (+3.9%) | 3285 MiB (-45.3%) | 8157 MiB (-24.2%) |
| SDNQ INT8 full pipeline | `WaveCut/Anima-Preview-3-SDNQ-int8-diffusers` | 3.5 GiB (-34.1%) | 22.41s | 4.60s/img | 1.38x (+38.4%) | 4111 MiB (-31.5%) | 8961 MiB (-16.7%) |

Quant-to-quant tradeoff in the full-pipeline run: UINT4 is 22.7% smaller than INT8 and uses 826 MiB less VRAM after load plus 804 MiB less peak generation VRAM. INT8 is 1.33x faster than UINT4 on this RTX 5090 setup.

## Prompting

Anima was trained on Danbooru-style tags, natural language captions, and mixtures of both. The upstream Anima Preview 3 card recommends about 1MP generation, for example `1024x1024`, `896x1152`, or `1152x896`, with roughly 30-50 steps and CFG 4-5.

Recommended positive prefix:

```text
masterpiece, best quality, score_7, safe,
```

Recommended negative prompt:

```text
worst quality, low quality, score_1, score_2, score_3, artist name
```

Use lowercase tags with spaces instead of underscores, except score tags such as `score_7`. For artist tags, prefix the artist with `@`.

## Notes

The original Anima split checkpoint is a ComfyUI-native model with a Qwen3 text encoder and a learned LLM adapter. Earlier transformer-only exports that load the checkpoint directly as `CosmosTransformer3DModel` ignore the `llm_adapter.*` weights; this component repo intentionally only stores the quantized transformer. Use the companion full Diffusers checkpoint for generation.

License follows the upstream Anima/CircleStone non-commercial license and the NVIDIA Cosmos derivative terms referenced by the upstream model card.