The SANA transformer and DC-AE VAE are Apache-2.0. The bundled gemma-2-2b-it text encoder is under the Gemma Terms of Use.

SANA-Sprint 1.6B 1024px β€” SceneWorks MLX mirror

Un-gated, repackaged mirror of Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers for the SceneWorks native MLX worker (mlx-gen-sana). SANA-Sprint is the few-step, CFG-free distillation of SANA (continuous-time consistency / SCM sampler + a guidance-embedding trunk) β€” ~2-step 1024Γ—1024 gen.

The tensors are copied dtype-preserving (BF16 trunk, F32 DC-AE) into the layout that SanaPipeline::new_sprint / from_snapshot expects:

transformer/diffusion_pytorch_model.safetensors   # SANA-Sprint 1.6B Linear-DiT trunk (BF16)
vae/diffusion_pytorch_model.safetensors           # 32x DC-AE f32c32 decoder (F32)
text_encoder/gemma-2-2b-it.safetensors            # gemma-2-2b-it CHI caption encoder (BF16)
text_encoder/tokenizer.json

The only modification is a header-level rename of the transformer ff sub-module keys (inverted_conv.conv/depth_conv.conv/point_conv.conv β†’ conv_inverted/conv_depth/conv_point); tensor bytes are unchanged. The gemma-2-2b-it text encoder is sourced from the un-gated SceneWorks/gemma-2-2b-it mirror (merged from its two shards) so the snapshot is self-contained.

License

The SANA-Sprint transformer and DC-AE VAE weights are licensed under the Apache License 2.0 (see LICENSE). NVIDIA relicensed them from the earlier non-commercial NVIDIA license to Apache-2.0 on 2026-07-31 in Efficient-Large-Model/Sana_Sprint_1.6B_1024px@449693db and Efficient-Large-Model/Sana_Sprint_1.6B_1024px_diffusers@19683c58 ("Relicense model under Apache-2.0"). The weight files are byte-identical before and after that relicence, so the grant covers the bytes mirrored here.

The bundled gemma-2-2b-it text encoder (text_encoder/ in every tier) is provided under and subject to the Gemma Terms of Use found at https://ai.google.dev/gemma/terms (copy: GEMMA_TERMS_OF_USE), including the use restrictions of the Gemma Prohibited Use Policy (https://ai.google.dev/gemma/prohibited_use_policy, copy: GEMMA_PROHIBITED_USE_POLICY.md). Those restrictions apply to anyone who uses or redistributes the text encoder.

See NOTICE. This mirror adds no additional grant.

Downloads last month

-

Downloads are not tracked for this model. How to track
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support