Gestura-FastH3-LiteRT
Gestura app capabilities and measured performance
| Generation mode | Input | 256 × 256 | 384 × 384 | Audio |
|---|---|---|---|---|
| Text-to-video (T2VA) | Text prompt | Preview, 5 s, 10 s | 5 s | Yes |
| First-frame image-to-video (I2VA) | Text prompt + one image | Preview, 5 s, 10 s | 5 s | Yes |
| Reference-conditioned video (REF2VA) | Text prompt + up to two reference inputs, at most one video | Preview, 5 s, 10 s (10 s: no video references) | — | Yes |
App-level measurements on Samsung Galaxy S26 (SM-S9420), 256 × 256, 5-second output option (124 frames), 24 fps:
| App input mode | Approximate generation time |
|---|---|
| Text → video with audio | ~431 s (7 min 11 s) |
| First-frame image → video with audio | ~460 s (7 min 40 s) |
| Two reference images → video with audio | ~601 s (10 min 01 s) |
Whole-app generation times; performance varies by input and device conditions.
Related models
| Repository | Contents |
|---|---|
| FastH3 LiteRT (this repository) | FastH3 denoising graphs and weights |
| Video VAE LiteRT | INT8 video encoder and decoder |
| FastH3 GGUF | Q4_K_M denoising model |
| REF2VA Delta | Reference-conditioned generation weight-delta package |
| Video VAE GGUF | Q8_0 video VAE |
On-device video examples
Four screen recordings from Gestura on Samsung Galaxy S26, showing generated video with audio.
Download Gestura
Gestura is an Android app for on-device AI generation, including text-to-video, first-frame image-to-video and reference-conditioned video with audio. The models in these repositories were converted or packaged during its development.
Model overview
FastH3 denoising graphs exported to the TensorFlow Lite (.tflite) format for LiteRT execution. The package includes four step-specific graph variants and their shared external weights, derived from the FastH3 four-step Dense release.
These assets were converted or packaged during Gestura development and are available for integration into other projects under the licenses below.
| Property | Value |
|---|---|
| Format | TensorFlow Lite graphs + external binary weights |
| Model payload size | 11.83 GB (decimal) |
| Model payload files | 5 |
| Integrity metadata | files.json, with sizes and SHA-256 hashes |
Repository contents
| Path | Contents |
|---|---|
fasth3_denoiser_variant*.tflite | Four denoiser graph variants |
weights/ | Shared external model weights |
| package.json | Graph signatures, input/output descriptions and weight bindings |
Model usage
Read package.json to select the graph variant and its signature. Preserve the relative weights/ paths and bind the declared external weights before invoking the graph with LiteRT CompiledModel. Use the declared input/output shapes and dtypes when preparing conditioning and latent tensors. The denoiser is a component of a video generation pipeline; scheduling and media decoding are supplied by the host implementation.
License and attribution
The model assets remain subject to the MiniMax H3 Community License Agreement, including its Acceptable Use Policy (Exhibit A). Read the complete LICENSE and NOTICE; this summary does not replace them.
- Territory restrictions exclude the European Union, United Kingdom, Republic of Korea and United States; separate authorization is needed for uses not granted by the agreement.
- Annual commercial revenue above USD 20 million requires prior written MiniMax authorization. Commercial products/services must prominently display MiniMax H3 in their UI.
- Redistribution requires the agreement, attribution and modification notices. Downstream terms, access/use safeguards and abuse reporting obligations also apply.
- The agreement restricts improving other AI models, imposes acceptable-use rules, and requires disclosure of publicly shared AI-generated content. Warranty, liability, termination and other provisions remain applicable.
Converted or packaged by Gestura; original model rights remain with the respective upstream owners. No upstream endorsement is implied.
Upstream: FastVideo/FastVideo-FastH3-4-step-Preview-v1-Dense-DataFree · MiniMaxAI/MiniMax-H3.