Model Gallery

10 models from 1 repositories

Filter by type:

Filter by tags:

minimax-h3-fl2va-q4

MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly from a text prompt, so a clip comes back as an MP4 with a real soundtrack rather than a silent render: ask for speech in the prompt and the model lip-syncs it. This is the Q4_K_M quantisation of the FL2VA partition, which serves text-to-video (t2va) and first/last-frame conditioning (fl2va). Reference conditioning (ref2va) is a different checkpoint and is refused by this one. Roughly 40 GB of weights across five files, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow — measured at roughly 176 s per denoise step at that canvas on a 20-SM device, so the 50-step default is a multi-hour job. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

minimax-h3-ref2va-q4

MiniMax-H3 served by vllm.cpp, LocalAI's own C++ port of vLLM. It generates video AND audio jointly, so a clip comes back as an MP4 with a real soundtrack rather than a silent render. This is the Q4_K_M quantisation of the Ref2VA partition, the one that takes REFERENCE conditioning: a reference image, a reference clip, or reference audio, prepended as their own blocks so the subject or style carries into the generated video. For plain text-to-video or first/last-frame conditioning use minimax-h3-fl2va-q4 instead - the two partitions are separate checkpoints and each refuses the other's tasks. Use this Q4_K_M build, NOT the NVFP4 Ref2VA weights: NVFP4 renders a multicolour patch grid, and it took three investigations upstream to establish that the fault is the quantisation rather than the reference path. On Q4_K_M the same code renders coherently. Roughly 40 GB of weights across five files, plus the two VAE configs that carry the latent statistics. The default canvas is 1344x768 at 124 frames and 24 fps, about 5.2 seconds. Generation is slow - roughly 176 s per denoise step at that canvas on a 20-SM device, so the 50-step default is a multi-hour job. Muxing the finished frames needs ffmpeg on the host.

Repository: localaiLicense: other

ltx-2

**LTX-2** is a DiT-based audio-video foundation model designed to generate synchronized video and audio within a single model. It brings together the core building blocks of modern video generation, with open weights and a focus on practical, local execution. **Key Features:** - **Joint Audio-Video Generation**: Generates synchronized video and audio in a single model - **Image-to-Video**: Converts static images into dynamic videos with matching audio - **High Quality**: Produces realistic video with natural motion and synchronized audio - **Open Weights**: Available under the LTX-2 Community License Agreement **Model Details:** - **Model Type**: Diffusion-based audio-video foundation model - **Architecture**: DiT (Diffusion Transformer) based - **Developed by**: Lightricks - **Paper**: [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://arxiv.org/abs/2601.03233) **Usage Tips:** - Width & height settings must be divisible by 32 - Frame count must be divisible by 8 + 1 (e.g., 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97, 105, 113, 121) - Recommended settings: width=768, height=512, num_frames=121, frame_rate=24.0 - For best results, use detailed prompts describing motion and scene dynamics **Limitations:** - This model is not intended or able to provide factual information - Prompt following is heavily influenced by the prompting-style - When generating audio without speech, the audio may be of lower quality **Citation:** ```bibtex @article{hacohen2025ltx2, title={LTX-2: Efficient Joint Audio-Visual Foundation Model}, author={HaCohen, Yoav and Brazowski, Benny and Chiprut, Nisan and others}, journal={arXiv preprint arXiv:2601.03233}, year={2025} } ```