seedance-storyboard-grid-to-video

Storyboard grid to video · Storyboard grid to video

Two stages: first a single-page sheet of numbered panels from an image model, then that sheet fed to Seedance as the reference. The sheet owns order, framing and timing, and the video prompt only has to connect the panels.

This Skill carries one prompt structure distilled from 14 human-verified Seedance cases on goodcase.ai. It is a sibling of seedance-prompt-library (all templates in one Skill); install this one when you only want this kind of clip. Do not invent structure from general video-generation knowledge: follow the structure below and ground the draft in one anchor case from references/cases.md.

Use when

• Multi-shot pieces where you want to see and fix the shot order before spending a generation: recipe sequences, action previs, product commercials, day-in-the-life montages.
• Chinese: Multi-shot films where you want to see and finalize the shot order before output: production processes, action previews, product ads, day-in-the-life montage transitions.

Workflow

1. Collect inputs. Ask only for what is missing: subject or product, setting, duration, aspect ratio, whether reference images / audio exist, and which language the final prompt should be in.
2. Pick one anchor case. Read references/cases.md, choose the case closest to the request, and name it in the reply. One anchor, never an average of several.
3. Fill the structure block by block. Every block below must be present in the final prompt; an empty block is where prompts go vague.
   1. Image prompt header: single-page sheet, aspect ratio, panel count, and the drawing style stated as premium storyboard, infographic poster or rough pencil previs
   2. Information cards: title, total runtime, number of shots, audio direction, so timing and panel count agree
   3. Panel list, one line each: shot size, the action happening in it, and what that panel is for
   4. Image prompt tail: the annotation system, and the exclusions such as no timestamps, no extra characters, no watermark
   5. Video prompt opening: name which image is the character reference and which is the storyboard, and what each one controls
   6. Rule list: follow 1 to N in order, one shot per panel, seconds per shot, no skipped or added steps, character and set stay identical
   7. Overall look and close: lighting, camera movement, audio, and the no-subtitle no-watermark tail
4. Apply the guidance and check the pitfalls (next two sections) before returning anything.
5. Return the finished prompt as one copy-pasteable block, the anchor case link, and a three-line checklist of what to verify in the generated video.

Guidance (from the cases)

• Tie panel count to runtime already in the image prompt. The croissant sheet puts TOTAL VIDEO TIME: 12 SECONDS and 8 SHOTS in the header and recounts it in the footer as 8 shots × 1.5s = 12 seconds.
• Give the two reference images separate jobs. The disaster-run case defines Image1 as the EXACT main character reference and Image2 as the EXACT storyboard design and layout reference.
• Say plainly which reference wins. The European summer walk writes Do not copy any pose or layout from the Master Character Set and hands locations, actions, compositions and sequence to the storyboard.
• Make step two a short list of hard rules. The croissant video prompt lists Follow the sequence exactly from 1 to 8, One shot per panel, approximately 1.5 seconds each and No skipped steps.
• Write each panel as an action plus a shot size, never as a picture. The kung-fu sheet numbers twelve lines like begin mid-air with a flying diagonal kick already in motion and requires Every panel must contain visible motion.

Pitfalls

• Baking timecodes into the sheet. Panel timestamps get drawn as artwork and carried into the video; the kung-fu sheet writes No timestamps and leaves timing to the rules in step two.
• More panels than the runtime can hold. Work backwards at 1.5 to 3 seconds per panel — the croissant sheet pairs 8 panels with a 12-second video.
• Letting the character sheet and the storyboard fight. The model copies poses off the character sheet; state that the storyboard controls locations, actions, compositions and sequence, and the character sheet only controls the face.
• Panels that describe a picture and no movement. The video comes out as a slideshow; give every panel something already in motion.

Language

Reply in the user's language. The prompt itself can stay in English when that is what the user's Seedance workflow expects; ask if unclear. The Chinese version of this structure follows.

Chinese: Storyboard grid to video

Two steps: first use an image model to generate a single-page storyboard image with numbered panels, then feed that image as a reference to Seedance. The order, composition, and duration are locked by the storyboard image; the video prompt is only responsible for connecting the panels.

Structure:

1. Image prompt opening: single-page storyboard, aspect ratio, number of panels; write the style as premium storyboard, infographic poster, or pencil sketch preview
2. Info card: title, total duration, number of shots, audio direction, so that duration and panel count match up
3. Panel-by-panel list, one panel per line: shot size, the action happening in this panel, what this panel is for
4. Image prompt closing: annotation system, and exclusions, such as no timecode, no extra characters, no watermark
5. Video prompt opening: name which one is the character reference and which one is the storyboard reference, and what each controls
6. Rules list: follow 1 to N, one panel one shot, how many seconds per shot, do not skip steps or add scenes, keep characters and scenes consistent throughout
7. Overall texture and closing: lighting, camera movement, audio, and finally write no subtitles or watermark

Key points:

• The panel count and total duration are locked in at the image generation step. The header of the croissant storyboard image says TOTAL VIDEO TIME: 12 SECONDS and 8 SHOTS, and the footer calculates it again 8 shots × 1.5s = 12 seconds。
• Make the division of labor between the two reference images clear. The disaster escape one defines Image1 as the EXACT main character reference, and Image2 as the EXACT storyboard design and layout reference。
• State clearly who is in charge. The European summer stroll one says Do not copy any pose or layout from the Master Character Set, handing the location, action, composition, and order entirely to the storyboard image.
• Write the second step as a small set of hard rules. The video prompt for the croissant one lists Follow the sequence exactly from 1 to 8、One shot per panel, approximately 1.5 seconds each and No skipped steps。
• Write each panel as action plus shot size, not as a picture. The twelve lines of the kung fu storyboard image are all begin mid-air with a flying diagonal kick already in motion sentences like this, and require Every panel must contain visible motion。

Common pitfalls:

• Drawing timecodes into the storyboard image. Timestamps on the panels will be carried into the video as image content; the kung fu one directly writes No timestampsin the image generation section, and leaves duration to the rules list in the second step.
• The number of panels exceeds what the duration can hold. Work backward from 1.5 to 3 seconds per panel; the croissant one is 8 panels with 12 seconds.
• The character image and the storyboard image conflict. The model will copy the pose from the character image; you must specify that the storyboard image controls location, action, composition, and order, while the character image only controls appearance.
• Write only the image in the panels, not the action. When the film starts moving, it is just a slideshow of several still images; each panel must be given an action that is happening.

Copy-ready lead-in / Copy-ready lead-in

For users who would rather paste into a chat model than run this Skill, hand them this line above the structure:

I want to make the storyboard sheet first and then turn it into video. [The story: a stray cat finding its way home through a rainy night, in 9 panels.] [Pixar-style 3D look, 15 seconds total.] Using the prompt template below, write both prompts for me: first the one that generates the storyboard sheet, then the Seedance prompt that turns that sheet into video:

I want to first generate a storyboard image and then turn it into a video, [the story is about a stray cat finding its way home on a rainy night, divided into 9 panels], [the style is like Pixar 3D, total duration 15 seconds]. Please follow the prompt template below to write the prompt in two steps: first write the prompt for generating the storyboard image, then write the Seedance prompt for turning this storyboard image into a video:

Notes

• references/cases.md is generated from data/ in LearnPrompt/awesome-seedance and refreshed daily; do not hand-edit an installed copy.
• Prompts in the reference file belong to their creators (linked on every card). Transfer the structure; do not present a close copy as original work.
• For the full library across every model, install the goodcase Skill from LearnPrompt/goodcase-lite.