Video prompts
Each video model has its own idea of a good prompt. Find the model below, read its guide in references/, and write the prompt the way that guide describes. If you switch models, switch guides.
Model guides
Model (create_video) |
Guide |
seedance-25 |
references/bytedance-seedance-2.5.md |
seedance, seedance-mini |
references/bytedance-seedance-2.0.md |
minimax-h3 |
references/minimax-h3.md |
kling |
references/kling-v3.md |
veo, veo-fast |
references/google-veo-3.1.md |
gemini-omni |
references/google-gemini-omni-1.1-flash.md |
flux-3 |
references/black-forest-labs-flux-3-video.md |
grok, grok-15 |
references/xai-grok-imagine.md (video sections) |
wan-3 |
references/alibaba-wan-3.0.md |
pika |
references/pika-2.5.md |
Apps that render on Seedance 2.5 (product_ad, podcast_creator and swap-anything) use its guide wherever they take free text for the video.
In Pika
- The prompt goes in the tool's
prompt field or the preset's prompt slot. Some apps build the prompt from other fields; fill those instead.
- Keep the user's intent and words. Expand a described look ("more cinematic", "like a perfume ad") into the concrete craft the guide asks for; don't invent a different idea.
- References are named by kind and position —
@image1, @video1, @audio1 — in the order of image_urls, video_urls, audio_urls. Where a guide says "the first image" or "Image 1", use these handles.
- Duration, aspect ratio, resolution and audio on/off are fields, and their descriptions give each model's limits. Keep them out of the prompt.
- A guide may mention a control the tool doesn't expose, such as a negative prompt or a seed. Restate a negative as the wanted result inside the prompt, or leave it out.
minimax-h3: send a first frame (image_url, optional end_image_url) or a reference set (image_urls, video_urls, audio_urls), not both. Reference audio needs an image or clip alongside it.
- Multi-shot (
seedance-25, up to 30 s): one line per shot, timecoded and consecutive, each with its own framing, action and end point, ending in "Hard cut.": Shot 1 (0–6 s): … Hard cut. One camera move per shot. Describe each character, product and place identically in every shot.
Defaults when a guide is silent
- Write prose, not keyword lists.
- Describe what you want in frame, not what to avoid ("steady camera", not "no shake").
- Be concrete: subject, action, setting, camera, light, style; add audio where the model renders it.
- For image-to-video and edits, describe only what moves or changes, and name what must stay the same.
- Fit the action to the duration: a 5 s clip holds one beat.
- Put dialogue in the format the model's guide expects.
1---2name: prompt-video3description: Use when writing or improving the prompt for a Pika video run — text-to-video, image-to-video, references, a multi-shot video or a video edit — before running it. Routes each model to its maker's own prompt guide.4metadata:5 source: https://skillmd.com/skills/pika-labs/prompt-video6---78# Video prompts910Each video model has its own idea of a good prompt. Find the model below, read its guide in `references/`, and write the prompt the way that guide describes. If you switch models, switch guides.1112## Model guides1314| Model (`create_video`) | Guide |15| --- | --- |16| `seedance-25` | `references/bytedance-seedance-2.5.md` |17| `seedance`, `seedance-mini` | `references/bytedance-seedance-2.0.md` |18| `minimax-h3` | `references/minimax-h3.md` |19| `kling` | `references/kling-v3.md` |20| `veo`, `veo-fast` | `references/google-veo-3.1.md` |21| `gemini-omni` | `references/google-gemini-omni-1.1-flash.md` |22| `flux-3` | `references/black-forest-labs-flux-3-video.md` |23| `grok`, `grok-15` | `references/xai-grok-imagine.md` (video sections) |24| `wan-3` | `references/alibaba-wan-3.0.md` |25| `pika` | `references/pika-2.5.md` |2627Apps that render on Seedance 2.5 (`product_ad`, `podcast_creator` and `swap-anything`) use its guide wherever they take free text for the video.2829## In Pika3031- The prompt goes in the tool's `prompt` field or the preset's `prompt` slot. Some apps build the prompt from other fields; fill those instead.32- Keep the user's intent and words. Expand a described look ("more cinematic", "like a perfume ad") into the concrete craft the guide asks for; don't invent a different idea.33- References are named by kind and position — `@image1`, `@video1`, `@audio1` — in the order of `image_urls`, `video_urls`, `audio_urls`. Where a guide says "the first image" or "Image 1", use these handles.34- Duration, aspect ratio, resolution and audio on/off are fields, and their descriptions give each model's limits. Keep them out of the prompt.35- A guide may mention a control the tool doesn't expose, such as a negative prompt or a seed. Restate a negative as the wanted result inside the prompt, or leave it out.36- `minimax-h3`: send a first frame (`image_url`, optional `end_image_url`) or a reference set (`image_urls`, `video_urls`, `audio_urls`), not both. Reference audio needs an image or clip alongside it.37- Multi-shot (`seedance-25`, up to 30 s): one line per shot, timecoded and consecutive, each with its own framing, action and end point, ending in "Hard cut.": `Shot 1 (0–6 s): … Hard cut.` One camera move per shot. Describe each character, product and place identically in every shot.3839## Defaults when a guide is silent4041- Write prose, not keyword lists.42- Describe what you want in frame, not what to avoid ("steady camera", not "no shake").43- Be concrete: subject, action, setting, camera, light, style; add audio where the model renders it.44- For image-to-video and edits, describe only what moves or changes, and name what must stay the same.45- Fit the action to the duration: a 5 s clip holds one beat.46- Put dialogue in the format the model's guide expects.