Skip to main content
The prompt is where H3’s multimodal training pays off: shots, camera moves, dialogue, and sound effects all live in one prompt block. This page collects the prompt writing resources for MiniMax H3 in ComfyUI: MiniMax’s official guides, general tips that apply to every workflow, and prompt embeddings for style effects.

​
Official guides

MiniMax publishes two official prompt writing guides:
  • Base generation modes (T2VA, I2VA, FL2VA, L2VA): structure a prompt into timed shots with camera movement and audio (dialogue, SFX, music), with examples for each mode
  • Full-reference mode (R2V): the rewrite output structure, including subject definitions, reference labels, and retention analysis, and how to assign each reference a role in the target shot
MiniMax also publishes installable H3 skills, including a prompt-writing skill that packages these guides for agent use. The workflow pages show these guides applied to each template: T2V and I2V, R2V, Multiframe Reference, and Fun ControlNet Union.

​
General tips

  1. Describe the whole scene: State the overall scene first (location, character, what is happening), then break it into timed shots
  2. Shots, camera, and audio: Describe the shots, camera moves, and the accompanying audio (dialogue, SFX, music) in one prompt block
  3. Resolution: H3’s native canvas is a 768px short edge, which is 1344x768 at 16:9, and resolutions are rounded to a multiple of 32. See Setting the output resolution
  4. Duration: The duration input snaps to the model’s 17-frame-per-block (17k+5) grid at 24fps
  5. On-screen text in quotes: Wrap any text that is visible on screen (signs, banners, subtitles, neon text) in English double quotation marks, and list each string separately. Community testing shows that enumerating every string in quotes keeps them legible, while undefined text tends to collapse into jumbled symbols. This follows the official base guide’s on-screen text rule. Keep spoken dialogue in <d> tags instead: quotes are for printed text, <d> is for what characters say
  6. Audio reuse markers in R2V: In full-reference (R2V) prompts, declare the audio’s relationship with a marker in the retention analysis: fully_copy uses the source audio 1:1 as the final audio track, while reference only carries timbre and delivery. Community-verified: without the correct marker, H3 treats the audio as a timbre reference only and lip movements drift out of sync with the lyrics. See the official full-reference guide’s relationship marker table
Workflow-specific prompting (reference tags, timeline anchors, control-video length) is covered on each workflow page.

​
Prompt embeddings

Comfy-Org/ComfyUI#15697 added support for prompt embeddings in MiniMax H3. You can use ComfyUI’s standard embedding: syntax in H3 prompts. Place an embedding file in ComfyUI/models/embeddings/ and reference it in the prompt by name, for example embedding:my_embedding. The embedding is loaded and mixed into the text conditioning just like with any other ComfyUI model. The Comfy-Org/MiniMax-H3 repository hosts 10 style embeddings in its embeddings folder. These files are unofficial: they were contributed by community member silveroxides via Hugging Face PR #50, and were not produced by Comfy-Org or MiniMax. The original files are in the silveroxides/MiniMax-H3_tests repository. The file name describes the intended effect, and the trigger word is the file name without the extension: