Downloads · 30 days
48.4K
98% of all-time downloads
Efficient-Large-Model/H3-to-LTX-Latent-Adapter
H3-to-LTX-Latent-Adapter is a machine learning model from Efficient-Large-Model. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for minimax-h3.
An original BF16 inference adapter that converts normalized MiniMax-H3 video latents into normalized LTX-2.5 Conv VideoVAE latents. It is used by Sol-H3-Spark in Sana.
Downloads · 30 days
48.4K
98% of all-time downloads
All-time downloads
49.2K
Public
Parameters
195M
390 MB on disk
Likes
3
Public
Click a slice to open those files.
.safetensors390 MB · 100%
From the Hugging Face model README
An original BF16 inference adapter that converts normalized MiniMax-H3 video latents into normalized LTX-2.5 Conv VideoVAE latents. It is used by Sol-H3-Spark in Sana.
The model applies the released temporal/spatial packing transform and a 194,759,504-parameter Conv3D residual adapter (width 752, 22 blocks). It does not contain MiniMax-H3 or LTX model weights and does not generate video alone.
| Boundary | Tensor |
|---|---|
| Input | Normalized H3 latent, [B, 24, T_h3, H/16, W/16] |
| Output | Normalized LTX latent, [B, 128, T_ltx, H/32, W/32] |
Pass the original pixel-frame count and pixel geometry to the adapter's
convert method. The inference library in Sana performs the matching packing
and normalization. Changing that transform is not interchangeable with this
checkpoint.
Files:
model.safetensors: BF16 adapter weights, 389,541,112 bytes.config.json: architecture, geometry and normalization contract.Weight SHA-256:
170199a390c40ac97f5895bc9c8cc29817e74fb9193c858a85d8c0f1f30724ac.
This model card does not assign a new weight license. MiniMax-H3 and LTX components used with the adapter remain subject to their respective terms.