> ## Documentation Index > Fetch the complete documentation index at: https://docs.comfy.org/llms.txt > Use this file to discover all available pages before exploring further. # ComfyUI MiniMax H3 Prompt Guide: Official Guides, Tips, and Prompt Embeddings > Write better MiniMax H3 prompts in ComfyUI: MiniMax's official prompt guides, general prompting tips, dialogue and speaker rules, and style embeddings. H3 expects shots, camera, dialogue, and SFX in one multimodal prompt. This page collects official guides, cross-workflow tips, shot/dialogue rules, and style embeddings. ## Official guides * [Base modes](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_base_en.md) (T2VA, I2VA, FL2VA, L2VA): timed shots, camera, audio * [Full-reference mode](https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/VIDEO_PROMPT_WRITING_GUIDE_ref_en.md) (R2V): rewrite structure, reference labels, retention markers Installable [H3 skills](https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills) package these for agents. Applied per template: [T2V/I2V](https://docs.comfy.org/tutorials/video/minimax/minimax-h3-native.md), [R2V](https://docs.comfy.org/tutorials/video/minimax/minimax-h3-native.md#minimax-h3-reference-to-video-r2v), [Multiframe](https://docs.comfy.org/tutorials/video/minimax/minimax-h3-multiframe.md#prompt-writing-guide), [Fun ControlNet](https://docs.comfy.org/tutorials/video/minimax/minimax-h3-fun-controlnet.md#prompting-tips). ## General tips I2VA opens with a fixed image-alignment line, blank line, then body fields. FL2VA/L2VA use their own alignment line; T2VA starts at the fields directly: ```text theme={null} integrated_multimodal_description: [Shot 1] ... overall_soundscape: ... non_diegetic_music: ... ``` Write prompts in **English**. Dialogue/lyrics in `` tags; on-screen text verbatim in its original language. 1. **Scene first**: Overall scene, then timed shots inside `[Shot 1]` of `integrated_multimodal_description` 2. **One block**: Shots, camera, and audio together 3. **Resolution**: Native **1344×768** at 16:9; multiples of **32** 4. **Length**: `length` is frames at 24fps (default **124** ≈ 5s), snapped to **17k+5** 5. **On-screen text**: English double quotes per string, verbatim (e.g. `A red neon sign reading "营业中"`). Spoken lines use ``, not quotes 6. **R2V audio markers**: In retention analysis, mark each audio ref as `fully_copy`, `partially_copy`, `reference`, or `weak_reference` to match how the clip is used (see official ref guide table) 7. **Audio fields**: `overall_soundscape` = ambient/SFX/non-verbal (1–4 sentences; `N/A` only if truly silent). Dialogue and diegetic music stay in shots. `non_diegetic_music` = score only (1–3 sentences; `N/A` if none). If unwanted speech appears, fill both fields explicitly 8. **No negatives**: `BasicGuider` runs at `cfg` 1 with no negative branch. Ban lists add unwanted concepts. State what should appear (or use R2V retention fields: `fully_preserved`, `partially_preserved`, etc.) 9. **Reference sheets (R2V)**: One image can hold multiple panels. Give the sheet its own `` (not only inside ``), describe panels, and point shots at a panel (e.g. full front view of ``). Label panels clearly Workflow-specific tags and controls live on each workflow page. ## Shots and cuts Number shots `[Shot 1]`, `[Shot 2]`, … `[Shot 1]` starts at 0.00s. Later shots open with a cut time: ```text theme={null} [Shot 2] At 00:03.500, the camera cuts to... ``` * Cut times increase and stay within clip duration (`length` at 24fps) * Use a single timestamp (`At 00:05.000`), not a range like `[5s-8s]` * Phrase cuts as actions: `the camera cuts to`, `the shot transitions to`, etc. Dissolves/fades/wipes when needed New shot when subject, space, state, viewpoint, or time changes. Small reframes stay one shot with camera motion. ## Dialogue and speakers * **Speaker IDs**: `(S1)`, `(S2)`, … for every voice (including off-screen/singing). IDs index speakers, not character numbers. Duet: `(S1,S2)` * **`` content**: ID, action, and delivery outside tags; inside tags, language tag + spoken words verbatim, in the shot paragraph where spoken * **Punctuation in ``**: Keep `, . ? !`; drop decorative repeats/emoji; end statements with `.` `?` `!` before ``; use `[unclear]` when unsure. Ellipses often hurt intelligibility * **Voiceover**: Use `says in an off-screen voiceover` and state lips stay closed after ``. Cross-cut dialogue: `` at both sides plus audio carries over * **Multi-speaker + audio refs**: Wrong-speaker assignment can happen. Tie lines to visible events, not timecodes. If needed, generate per-speaker audio externally and reference with the right marker (`fully_copy` vs `partially_copy`) ## Prompt embeddings [ComfyUI#15697](https://github.com/Comfy-Org/ComfyUI/pull/15697) supports `embedding:name` in H3 prompts. Place files in `ComfyUI/models/embeddings/`. [Comfy-Org/MiniMax-H3/embeddings](https://huggingface.co/Comfy-Org/MiniMax-H3/tree/main/embeddings) lists **10** community style embeddings ([silveroxides](https://huggingface.co/silveroxides), [discussion #50](https://huggingface.co/Comfy-Org/MiniMax-H3/discussions/50); unofficial). Trigger word = filename without extension: | Embedding | Effect (by name) | | - | - | | `minimaxh3_art_is_explosion` | Explosive art composition | | `minimaxh3_blooming_flowers` | Flowers blooming | | `minimaxh3_bullet_time` | Bullet-time effect | | `minimaxh3_dark_magic` | Dark magic atmosphere | | `minimaxh3_fire_breath` | Fire-breath effect | | `minimaxh3_four_seasons` | Four seasons transition | | `minimaxh3_kiss_camera` | Kiss scene camera move | | `minimaxh3_spiral_ascent` | Spiraling ascent | | `minimaxh3_storm_magic` | Storm magic | | `minimaxh3_truman_show` | Truman Show style | This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.