Multimodal RL training framework for diffusion & omni models
-
Updated
Sep 6, 2026 - Python
#
minimax-h3
Here are 206 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
A native .NET LLM inference engine for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, and Ollama/OpenAI-compatible HTTP APIs for programmatic access. It supports Windows/MacOS/iOS/Linux with full GPU capability
ai csharp metal dotnet cuda transformers inference glm gemma inference-engine multimodal cuda-programming llm qwen gguf deepseek-v4 qwen35 gemma4 dspark minimax-h3
-
Updated
Sep 6, 2026 - C#
Native macOS app for local AI video on Apple Silicon — LTX-2, LTX-2.3, LTX-2.5, and MiniMax H3
mac-app minimax mlx image-to-video text-to-video apple-silicon ltx-video mac-native ltx-2 ltx-2-5 ltx-2-5-ai minimax-h3
-
Updated
Sep 6, 2026 - Swift
Refine and improve the quality of small faces in MiniMax H3 video. Per-frame face tracking, crop, refine with H3, stitch back.
video-processing face-detection lipsync video-generation insightface diffusion-models face-restoration yolov8 face-enhancement generative-ai ai-video comfyui segment-anything comfyui-nodes comfyui-custom-node comfyui-custom-nodes comfyui-video minimax-h3
-
Updated
Sep 4, 2026 - Python
MiniMax-H3超级缓存加速插件
-
Updated
Aug 3, 2026 - Python
HarnessEval-W: Agentifying the Evaluation of Visual Worlds
agent benchmark evaluation harness wan video-generation world-model kling seedance harness-engineering minimax-h3
-
Updated
Sep 2, 2026 - Python
A timeline editor for MiniMax H3 inside ComfyUI - storyboard prompts, first/last keyframes, image/video/audio references, joint audio, live sampling preview, retakes and shot chaining.
storyboard minimax video-generation image-to-video text-to-video timeline-editor comfyui comfyui-nodes minimax-h3
-
Updated
Aug 16, 2026 - JavaScript
Run MiniMax Hailuo H3 and LTX-2.5 video generation locally on a Mac. Joint audio+video, character LoRA training, one-click Pinokio install. MLX — no CUDA, no cloud, no API key.
macos lora minimax mlx video-generation image-to-video diffusion-models text-to-video apple-silicon ai-video pinokio local-ai generative-video hailuo ltx-video ltx-2 minimax-h3
-
Updated
Sep 6, 2026 - Python
Creative DNA video prompt cases and installable Skills for MiniMax H3 and Seedance 2.0, with an Electron video viewer.
electron video-generation prompt-engineering ai-video codex-skills seedance-2-0 minimax-h3 creative-dna
-
Updated
Sep 6, 2026 - JavaScript
A comprehensive ComfyUI toolkit for video generation, image editing, and audio-driven lip‐sync, featuring Flux, MiniMax, LTX, Wan2.2 and advanced batch workflows.
-
Updated
Sep 3, 2026 - JavaScript
Multimodal MiniMax H3 prompt writer for ComfyUI with local and API providers.
-
Updated
Sep 6, 2026 - Python
ComfyUI custom nodes providing unified image and mask resizing with support for multiple scaling modes, aspect-ratio preservation, center crop alignment, and stable tensor-based mask transformations, and more.
-
Updated
Sep 6, 2026 - Python
Video Delta Net hybrid attention for MiniMax-H3 as a native ComfyUI node.
-
Updated
Sep 5, 2026 - Python
AI 短剧生产总控 / 短剧skill:专业导演与分镜、MiniMax H3、CompShare、声音资产、粗剪与 QC,默认 16:9。
ffmpeg storyboard chinese minimax filmmaking video-generation ai-video comfyui fish-audio codex-skill ai-short-drama short-drama minimax-h3
-
Updated
Aug 30, 2026 - JavaScript
MCWW: Additional non-node based UI for ComfyUI focused on inference. Stable UI states; presets; and advanced queue. Based on Gradio
pwa ai artificial-intelligence image-generation music-generation gradio video-generation image-edit audio-generation generative-ai comfyui comfyui-nodes minimax-h3
-
Updated
Sep 5, 2026 - Python
🎬 Curated MiniMax H3 video generation prompts — cinematic, ads, anime, UGC, product videos, and more. Includes playable examples and creator attribution.
webm awesome-list image-to-video text-to-video generative-ai ai-video multimodal-ai prompt-gallery video-prompts minimax-h3
-
Updated
Aug 18, 2026 - JavaScript
ComfyUI nodes and tested workflows for MiniMax H3 still-image generation, reference editing, and Qwen detail refinement.
image-editing text-to-image image-to-image generative-ai comfyui qwen-image-edit minimax-h3 reference-editing
-
Updated
Aug 19, 2026 - Python
NVIDIA Sol-Attn for ComfyUI / Triton kernel on SM89 - SM121, with zero-copy MiniMax H3 nodes: memory-efficient attention, scheduled tau with graph preview, and feed-forward chunking. Measured ×ばつ vs SageAttention and −37% MLP peak VRAM on H3
triton attention video-generation memory-optimization diffusion-models blackwell memory-op sparse-attention comfyui sageattention comfyui-custom-nodes trito minimax-h3 sol-attn
-
Updated
Aug 13, 2026 - Python
Real-time multimodal AI pipelines on Apple Silicon
-
Updated
Sep 6, 2026 - C++
Add this topic to your repo
To associate your repository with the minimax-h3 topic, visit your repo's landing page and select "manage topics."