ModelAufgelistetExtern

Wan 21 Onnx

ONNX export of Wan2.1-T2V-14B for ONNX Runtime (text-to-video). The 4-bit DiT runs 81 frames at 480×832 within 24 GB of VRAM.

Quellehuggingface.co/AkaneTendo25/wan21-onnx/tree/90a00380804ffe84a5ebe71c57cd968b2a21f68d

ArtOtherBasismodellWan-AI/Wan2.1-T2V-14BVersionDit fp16CBewertung

Modellquelle

Art: Other
Dateigröße: 725 KB–280 MB
Basismodell: Wan-AI/Wan2.1-T2V-14B
Version: vDit fp16
Aktualisiert: 20. Okt. 2026
Quelle: Hugging Face

Quellenbeschreibung

Wan2.1-T2V-14B — ONNX

ONNX export of Wan2.1-T2V-14B for ONNX Runtime (text-to-video). The 4-bit DiT runs 81 frames at 480×832 within 24 GB of VRAM.

Setup, usage, and conversion: https://github.com/AkaneTendo25/wannx

Files

File	Description	Size
`dit.onnx` (+ `.data`)	DiT, 4-bit `MatMulNBits`, fp16 attention	~7.8 GB
`dit_fp16.onnx` (+ `.data`)	DiT, fp16	~27 GB
`t5_encoder_fp16.onnx` (+ `.data`)	umt5-xxl text encoder	~13 GB
`vae_decoder.onnx` (+ `.meta.json`)	VAE decoder, streaming step graph (latents 1+) — any resolution, fits 24 GB	~0.3 GB
`vae_decoder_init.onnx`	VAE decoder, streaming init graph (latent 0) — bit-exact first frame	~0.3 GB
`google/umt5-xxl/`	tokenizer	~20 MB

License: Apache-2.0 (inherited from Wan2.1).

Quellen

1 Quelle

Hugging FacePrimärVersion 90a00380804ffe84a5ebe71c57cd968b2a21f68d

huggingface.co/AkaneTendo25/wan21-onnx/tree/90a00380804ffe84a5ebe71c57cd968b2a21f68d

Verifiziert 20. Okt.

Download files

Modellartefakte

5 Artefakte

dit_fp16.onnx

onnx · 9,60 MB · SHA-256 0e28440d157b…ce80 · Hugging Face

Download file

dit.onnx

onnx · 8,89 MB · SHA-256 d7d6580e956c…445e · Hugging Face

Download file

t5_encoder_fp16.onnx

onnx · 725 KB · SHA-256 c71e13bd1356…3683 · Hugging Face

Download file

vae_decoder_init.onnx

onnx · 273 MB · SHA-256 05ad78cfcda9…709f · Hugging Face

Download file

vae_decoder.onnx

onnx · 280 MB · SHA-256 53f5f511bfdf…3d0a · Hugging Face

Download file

Quellenauszüge

2 Auszüge

Readme3. Aug.huggingface.co/AkaneTendo25/wan21-onnx

--- license: apache-2.0 base_model: Wan-AI/Wan2.1-T2V-14B pipeline_tag: text-to-video tags: - onnx - onnxruntime - text-to-video - wan2.1 --- # Wan2.1-T2V-14B — ONNX ONNX export of [Wan2.1-T2V-14B](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B) for ONNX Runtime (text-to-video). The 4-bit DiT runs 81 frames at 480×832 within 24 GB of VRAM. **Setup, usage, and conversion: https://github.com/AkaneTendo25/wannx** ## Files | File | Description | Size | |---|---|---| | `dit.onnx` (+ `.data`) | DiT, 4-bit `MatMulNBits`, fp16 attention | ~7.8 GB | | `dit_fp16.onnx` (+ `.data`) | DiT, fp16 | ~27 GB | | `t5_encoder_fp16.onnx` (+ `.data`) | umt5-xxl text encoder | ~13 GB | | `vae_decoder.onnx` (+ `.meta.json`) | VAE decoder, streaming step graph (latents 1+) — any resolution, fits 24 GB | ~0.3 GB | | `vae_decoder_init.onnx` | VAE decoder, streaming init graph (latent 0) — bit-exact first frame | ~0.3 GB | | `google/umt5-xxl/` | tokenizer | ~20 MB | License: Apache-2.0 (inherited from Wan2.1).

Note3. Aug.huggingface.co/AkaneTendo25/wan21-onnx

Source context: 0 downloads · 0 likes · Pipeline text-to-video · Repo AkaneTendo25/wan21-onnx