MiniMaxAI/MiniMax-H3
PulseAugur coverage of MiniMaxAI/MiniMax-H3 — every cluster mentioning MiniMaxAI/MiniMax-H3 across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Alibaba-pai releases MiniMax-H3-Acc-LoRAs for efficient video generation
Alibaba-pai has released MiniMax-H3-Acc-LoRAs, a model designed for efficient video generation. This model utilizes Parallel Decoding Distillation (PDD) to achieve fast video creation in a minimal number of inference st…
-
New MiniMax-H3 x Z-Image model enhances spatial detail in image generation
A new image generation model, joeygambino/MiniMax-H3-x-Z-Image-native, has been released on Hugging Face. This model combines Z-Image's spatial attention capabilities with the H3 engine, aiming to produce richer details…
-
New LoRA model offers 2.5x faster inference for MiniMax-H3
A new LoRA (Low-Rank Adaptation) model, lightx2v/Minimax-h3-Turbo-SLA, has been released, offering significant improvements in inference speed for the MiniMax-H3 model. This distilled model utilizes Sparse-Linear Attent…
-
Fal releases MiniMax H3 LoRA for enhanced realistic people generation
Fal has released a new LoRA adapter, MiniMax-H3-Realism-People-LoRA, designed to enhance the realism of human subjects in video generated by the MiniMax H3 model. This adapter focuses on improving facial details, skin t…
-
MiniMax-H3 omni-modal system ported to Apple Silicon via MLX
A new open-source Python package, MiniMax-H3-MLX, has been released to enable the MiniMax-H3 omni-modal generative system to run on Apple Silicon. This system can process text, images, audio, and video to generate up to…
-
Open-weight AI models gain traction on Hugging Face
Several open-weight AI models are gaining traction on Hugging Face, with MiniMaxAI/MiniMax-H3 leading in downloads and stars for its image-text-to-video capabilities. Other models like DeepSeek-V4-Flash-0731, DavidAU/Qw…