Downloads · 30 days
92
12% of all-time downloads
SceneWorks/wan2.2-i2v-a14b-mlx
wan2.2-i2v-a14b-mlx is a image-to-video model from SceneWorks. Use it for the image-to-video task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
Native MLX (Apple Silicon) conversion of Wan-AI/Wan2.2-I2V-A14B, packaged as a turnkey, self-contained snapshot for the SceneWorks app. Downloading this repo replaces the previous "download the native checkpoint and c…
Downloads · 30 days
92
12% of all-time downloads
All-time downloads
780
Public
Repo size
278 GB
Likes
0
Public
Click a slice to open those files.
.safetensors209 GB · 100%
From the Hugging Face model README
Native MLX (Apple Silicon) conversion of Wan-AI/Wan2.2-I2V-A14B, packaged as a turnkey, self-contained snapshot for the SceneWorks app. Downloading this repo replaces the previous "download the native checkpoint and convert on-device" first-run step.
Wan2.2 A14B is a high/low-noise mixture-of-experts image-to-video model — two transformers switched at the noise boundary.
| file | what |
|---|---|
high_noise_model.safetensors | high-noise expert DiT (~28.6 GB) |
low_noise_model.safetensors | low-noise expert DiT (~28.6 GB) |
t5_encoder.safetensors | UMT5-XXL text encoder (~11.4 GB) |
vae.safetensors | Wan z16 VAE |
tokenizer.json | UMT5 tokenizer |
config.json | architecture config (dual_model: true, in_dim: 36 image-concat) |
Quantization (Q4/Q8) is applied at load by the engine — these weights are full bf16.
Wan-AI/Wan2.2-I2V-A14B (Apache-2.0).mlx-gen-wan, converter id wan_i2v_14b), dtype bfloat16, dense (no baked-in quant).Apache-2.0, inherited from the upstream model. This repository redistributes a converted copy of the upstream Apache-2.0 weights, with attribution, as permitted by that license. See the source model card.