MiniMax-H3, an omni-modal generative model that combines multimodal context understanding with joint audio-visual generation in a shared latent framework, is the subject of a new evaluation examining …
Nunchux AI released VC-Attention, a training-free low-bit attention kernel for video Diffusion Transformers that delivers up to 3.58x attention speedup and 1.70x end-to-end speedup on the RTX 5090 at …
Uprouter added Hailuo Web (MiniMax), MiniMax's consumer chat product at chat.minimax.io, to its model directory, listing MiniMax-01 at $0.200 per 1M input tokens and $1.10 per 1M output tokens as the …
NVIDIA Research's Efficient AI Team and Singapore Lab reported that a two-stage pipeline specialized for a single NVIDIA DGX Spark generates a 384p draft and refines it to 768p, producing a 5-second 7…
A developer has released a CUDA-optimized fork of antirez's h3.c for NVIDIA DGX Spark, achieving a ~15.5x speedup, while also providing a native Apple Silicon implementation for MiniMax-H3 inference w…
MiniMax-H3, a 33-billion-parameter open-weight video generation model from Chinese AI firm MiniMax, ranks first in the Video Edit Arena on arena.ai with 1390 points, 32 points ahead of Dreamina Seedan…
Comfy-Org released MiniMax-H3, a multimodal video and audio generation model, and a tutorial demonstrates implementing an end-to-end pipeline using ComfyUI as a headless inference backend. The pipelin…
Antirez released h3.c, a native MiniMax-H3 inference engine for Apple Silicon Macs, with prompt-to-video/audio, first/last-frame conditioning, and ordered Ref2VA references working end to end. The pro…
PipeNetwork released minimax-h3-mlx, a community MLX implementation of MiniMax-H3 for Apple Silicon, translating the 33-billion-parameter video-and-audio diffusion pipeline into native MLX. The reposi…
Simon Willison successfully ran MiniMax-H3, a text-to-video model, on an Apple M5 Max MacBook Pro using the PipeNetwork/minimax-h3-mlx Python package, which ports the model to MLX. The process downloa…
A user attempting to load the MiniMax-H3 text-to-video model from Hugging Face on a machine with 96GB RAM and an R9700 32GB GPU reports that even with 8-bit quantization of the transformer and text en…