Generate MiniMax Hailuo 3.0 video clips through hosted APIs or local ComfyUI workflows.
npx skills add https://github.com/calesthio/OpenMontage --skill minimax-h3
Please help me install this Agent Skill. Skill: minimax-h3 Source: https://github.com/calesthio/OpenMontage/tree/main/.agents/skills/minimax-h3 Command: npx skills add https://github.com/calesthio/OpenMontage --skill minimax-h3
Choosing and configuring the right provider for MiniMax H3 (Hailuo 3.0) video generation is confusing because each platform uses different model identifiers, durations, and resolutions. This Skill routes text-to-video, image-to-video, first/last-frame, and reference-conditioned video requests to the correct provider with the correct parameters.
Ask the agent to generate a 10-second MiniMax H3 video from a text prompt describing the subject, camera path, and lighting using the MiniMax direct route.
High-intent search queries and answers about installing and using this skill.
Use the MiniMax direct route with model MiniMax-H3, or fal.ai, Runway, or ComfyUI Partner Nodes. Write a prompt covering subject, action, camera path, environment, lighting, and audio intent, and specify a concrete aspect ratio rather than adaptive.
Each provider uses a different model identifier: MiniMax-H3 for the first-party v2 API, hailuo-03 on fal.ai, and hailuo3 on Runway. The direct API outputs 2K at 4-15 seconds, while Runway supports 768P or 2K at 5-15 seconds.
Yes, the open-weight ComfyUI route runs fully offline once models are installed. Export the official workflow in API format and pass workflow_json or workflow_path plus output_node, with the diffusion model, Qwen3-VL text encoder, and video and audio VAEs.
Provide both the first and last frame images and describe the motion that should occur between them in the prompt. Keep the requested motion achievable within the 4-15 second clip duration.
Yes, reference-to-video accepts images, videos, and audio combined as conditioning inputs. Audio references require at least one visual reference alongside them.
ChatCut-IncGenerate AI video clips from text, images, and reference footage.
ChanghochienOrganize footage and generate initial rough cuts for post-production editing workflows.
aimentor606Run and compare AI/ML models via the Replicate API for media generation.
0xslineGenerate AI videos via Seedance 2.0, Kling, and MiniMax Hailuo models.
