Downloads · 30 days
34
32% of all-time downloads
anima-mlx
xocialize/anima-mlx
anima-mlx is a text-to-image model from xocialize. Use it when you need an image from a text prompt. It is set up for mlx. The card lists the license as other.
Pure-MLX port of circlestone-labs/Anima, an anime/illustration text-to-image model. The denoiser is NVIDIA Cosmos-Predict2-2B (CosmosTransformer3DModel); the text path is Qwen3-0.6B → a 6-block llmadapter; the decoder…
All-time downloads
106
Public
Repo size
6.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors6.9 GB · 100%
At a glance
- Task
- Text-to-Image
- Library
- mlx
- License
- other
- Access
- Public
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026
- SHA
- 4cc65eea
Base models
Model card
From the Hugging Face model README
Anima-MLX — anime text-to-image for Apple Silicon (MLX)
Pure-MLX port of circlestone-labs/Anima,
an anime/illustration text-to-image model. The denoiser is NVIDIA Cosmos-Predict2-2B
(CosmosTransformer3DModel); the text path is Qwen3-0.6B → a 6-block llm_adapter; the
decoder is the Qwen-Image / Wan 16-channel 3D-causal VAE.
Built on NVIDIA Cosmos. The base denoiser is licensed under the NVIDIA Cosmos Open Model License. The Anima fine-tune weights are Non-Commercial (CircleStone Labs). This MLX port is redistributed under the same Non-Commercial terms — personal / research use only, not for commercial use. Port code: MIT.
Parity
Every component is parity-locked against a PyTorch oracle, and the full pipeline against a torch reference (injected noise + identical token ids):
| stage | metric |
|---|---|
| Cosmos DiT | fp32 max_abs 3.1e-5 · bf16/GPU cos 0.999995 |
| llm_adapter | fp32 max_abs 2.9e-5 · bf16/GPU cos 0.999995 |
| Qwen3-0.6B TE | fp32 max_abs 6.1e-4 · bf16/GPU cos 0.999998 |
| Wan/Qwen-Image VAE | fp32 max_abs 7.5e-6 · bf16/GPU cos 0.999954 |
| e2e (text path) | max_abs 2.3e-6 |
| e2e (DiT-in-loop + CFG, step 0) | cos 1.0000000 |
| transformer int8 g128 | per-pass cos 0.99991 |
| transformer int4 g64 | per-pass cos 0.99628 |
Files
| file | dtype | resident |
|---|---|---|
transformer-bf16.safetensors | bf16 | 3.91 GB |
transformer-int4.safetensors | int4 (attn+ff, g64) | 1.38 GB |
llm_adapter-bf16.safetensors | bf16 | ~0.24 GB |
text_encoder-bf16.safetensors | bf16 | ~1.2 GB |
vae-bf16.safetensors | bf16 | ~0.25 GB |
Measured peak unified memory @512²: ~14 GB (bf16) / ~6 GB (int4 transformer).
Sampling
ComfyUI ModelType.FLOW — CONST prediction + ModelSamplingDiscreteFlow(shift=3, multiplier=1):
sigma(t) = 3t / (1 + 2t), DiT timestep == sigma ∈ [0,1], Wan21 latent denorm before decode.
CFG 4–5. Tokenizers: Qwen2.5 (raw BPE, pad 151643) + T5-v1.1 SentencePiece (32128, trailing eos).
Credits
- Anima — CircleStone Labs (Non-Commercial)
- Cosmos-Predict2 — NVIDIA (Cosmos Open Model License)
- Qwen3 — Alibaba · Wan VAE — Alibaba/Wan
- MLX port — xocialize
- Task
- Text-to-Image
- Library
- mlx
- License
- other
- Created
- Jun 27, 2026
- Updated
- Jun 27, 2026