Efficient-Large-Model / H3-to-LTX-Latent-Adapter

huggingface.co
Total runs: 1.3K
24-hour runs: 77
7-day runs: 219
30-day runs: 1.3K
Model's Last Updated: September 10 2026

Introduction of H3-to-LTX-Latent-Adapter

Model Details of H3-to-LTX-Latent-Adapter

H3-to-LTX Latent Adapter

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.

Runs of Efficient-Large-Model H3-to-LTX-Latent-Adapter on huggingface.co

1.3K
Total runs
77
24-hour runs
219
3-day runs
219
7-day runs
1.3K
30-day runs

More Information About H3-to-LTX-Latent-Adapter huggingface.co Model

H3-to-LTX-Latent-Adapter huggingface.co

H3-to-LTX-Latent-Adapter huggingface.co is an AI model on huggingface.co that provides H3-to-LTX-Latent-Adapter's model effect (), which can be used instantly with this Efficient-Large-Model H3-to-LTX-Latent-Adapter model. huggingface.co supports a free trial of the H3-to-LTX-Latent-Adapter model, and also provides paid use of the H3-to-LTX-Latent-Adapter. Support call H3-to-LTX-Latent-Adapter model through api, including Node.js, Python, http.

Efficient-Large-Model H3-to-LTX-Latent-Adapter online free

H3-to-LTX-Latent-Adapter huggingface.co is an online trial and call api platform, which integrates H3-to-LTX-Latent-Adapter's modeling effects, including api services, and provides a free online trial of H3-to-LTX-Latent-Adapter, you can try H3-to-LTX-Latent-Adapter online for free by clicking the link below.

Efficient-Large-Model H3-to-LTX-Latent-Adapter online free url in huggingface.co:

https://huggingface.co/Efficient-Large-Model/H3-to-LTX-Latent-Adapter

H3-to-LTX-Latent-Adapter install

H3-to-LTX-Latent-Adapter is an open source model from GitHub that offers a free installation service, and any user can find H3-to-LTX-Latent-Adapter on GitHub to install. At the same time, huggingface.co provides the effect of H3-to-LTX-Latent-Adapter install, users can directly use H3-to-LTX-Latent-Adapter installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

H3-to-LTX-Latent-Adapter install url in huggingface.co:

https://huggingface.co/Efficient-Large-Model/H3-to-LTX-Latent-Adapter

Url of H3-to-LTX-Latent-Adapter

Provider of H3-to-LTX-Latent-Adapter huggingface.co

Efficient-Large-Model
ORGANIZATIONS

Other API from Efficient-Large-Model