Back to directory

ComfyUI MiniMax H3 Prompt Writer

A ComfyUI UI extension that turns a plain-language creative brief and optional reference images, video, or audio into an editable MiniMax H3 video prompt, without running the model or queuing a render itself.

ComfyUI MiniMax H3 Prompt Writer

H3 Prompt Writer is a prompt-authoring workspace built into ComfyUI for MiniMax H3 video generation. A user writes a plain-language creative brief, attaches optional image, video, or audio references, and the extension formats an editable prompt in the structure H3 expects; it only writes that prompt text and prepares reference media, leaving the actual model run to the user's existing H3 workflow.

Its sequence mode drafts several related prompts from one brief with shared references and per-chunk edits, and a media panel offers a composer for building contact-sheet collages, an editor for cropping and trimming images and video, and a floating panel for dragging prepared media into a workflow. Prompt generation can call a local or remote model, including Ollama, a direct GGUF file, an external llama.cpp server, or a hosted API.

It ships as a ComfyUI extension and, separately, as a standalone Windows build, with a light theme and adjustable interface size.

More in Generative media

See all 146
  • Blender Copilot

    github.com

    A Copilot-style AI chat panel inside Blender that runs its agent loop in Blender's own Python process, executes the model's generated code against the live scene, and wraps every conversational turn in a single undo step.

  • A ComfyUI add-on that patches ComfyUI-GGUF so Qwen-Image-2.1 models can run fully as GGUF files, fixing a text-encoder mismatch and missing architecture detection until upstream support arrives.

  • A ComfyUI node that expands a short prompt into a full styled prompt, negative prompt and aspect ratio for Qwen-Image-2.1, using one of 17 photographic styles.