seedance-fashion-lookbook

Fashion lookbook and portrait film · 时尚 lookbook 与人像写真片

One person, one look, a handful of places. A head-to-toe appearance lock carries the whole clip, and each scene gets one location, one gesture and one kind of light.

This Skill carries one prompt structure distilled from 43 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

• Fashion campaigns, street-style lookbooks, outfit-change reels, and portrait or beauty pieces where the payload is how someone looks moving through a few settings.
• Chinese: Fashion advertising films, street-style lookbooks, outfit-change short films, and portrait and beauty photo films; the payload is simply what one person looks like across several scenes.

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. Header parameters: aspect ratio, exact duration, the genre stated as fashion campaign, Vogue editorial or cinematic portrait, and the cutting pace
   2. Person and look lock: face, hair, makeup, jewellery, then every garment, shoe and bag named, with a line saying it is identical in every scene
   3. Hero item lock: material, colour, hardware, and how it is carried
   4. Scene chain: each block marked with seconds or a scene number, carrying shot size, place, one action and the light
   5. On-screen type, when wanted, as its own short line under the scene it belongs to
   6. Closing hero beat: everything slows, the camera orbits or pushes onto the item, and the last move tilts up to the face
   7. Visual direction and exclusions: lens, film tone, grain, and no plastic skin, stiff poses or watermarks
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)

• Write the outfit head to toe in the opening paragraph, then say it travels. The Paris campaign runs all the way to black pointed-toe heels, babypink smooth leather hobo shoulder bag and closes with hanging naturally on arm throughout all scenes.
• Give each scene one shot size, one place and one gesture. The Paris case heads a block with Scene 5 · 3 sec Medium close-up, and the only action in it is slowly pushes sunglasses up with one finger.
• Lock the hero item apart from the person. The Tokyo bag film states One consistent young female fashion model throughout, then locks one identical glossy pastel-pink Prada handbag on its own line.
• For portrait-style pieces, chain the actions in one long sentence with no shot numbers. The stream walk runs from holding a juicy red watermelon slice near her face straight through to her turning to the camera on a wooden porch.
• Buy the photographic feel with gear plus an exclusion list. The Paris case names shot on Canon EOS R5 35mm f/1.4, Kodak Portra 400 film tone and rules out plastic skin, robotic movement, stiff poses.

Pitfalls

• Describing the outfit once in loose terms. Clothes drift between scenes; name every piece and add that it stays identical scene to scene.
• Packing three actions into a three-second block. One gesture per scene — the Paris case gives each three-second scene a single move.
• Handing the model a paragraph of on-screen copy. The Tokyo film only ever puts one or two short lines up, like TOKYO or MADE TO BE SEEN; longer type renders garbled, so add it in post.
• Running slow motion and transition effects the whole way. The Tokyo film pins its montage to hard cuts synchronized to the beat and saves the slowdown for the hero shot.

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: Fashion lookbook and portrait film

One person, one outfit, several locations. A head-to-toe appearance lock carries the entire film, with each scene giving only one location, one action, and one kind of light.

Structure:

1. Opening parameters: aspect ratio, exact duration, and genre written as fashion advertising film, Vogue editorial, or cinematic portrait, then set out the editing rhythm
2. Character and styling lock: face, hairstyle, makeup, jewelry, then name every piece of clothing, shoes, and bag, and add a line that it is the same in every scene
3. Hero product lock: material, color, hardware, and how it is held on the body
4. Scene chain: mark each segment with seconds or scene number, and write the shot size, location, one action, and lighting
5. For anything that needs on-screen text, put a short line on its own line under the corresponding scene
6. Closing hero shot: the whole thing slows down, the camera circles once or pushes in on the hero product, and finally tilts up to the face
7. Visual direction and exclusion list: lens, film tone, grain; exclude plastic skin, stiff poses, and watermarks

Key points:

• In the opening paragraph, write the styling from head to toe, then state clearly that it stays with them throughout. The Paris street-style one lists all the way to black pointed-toe heels, babypink smooth leather hobo shoulder bag, and at the end adds the line hanging naturally on arm throughout all scenes。
• Each scene gives only one shot size, one location, and one action. The subtitle for the Paris one is Scene 5 · 3 sec Medium close-up, and the only action in this segment is slowly pushes sunglasses up with one finger。
• Lock the hero product separately from the person. The Tokyo handbag one first writes One consistent young female fashion model throughout, then locks on a separate line one identical glossy pastel-pink Prada handbag。
• For the portrait-photo style, use one long sentence to string the actions together, without marking shot numbers. The creekside one goes from holding a juicy red watermelon slice near her face all the way to her turning back on the wooden porch and smiling at the camera.
• The photo texture comes from equipment plus an exclusion list. The Paris one names shot on Canon EOS R5 35mm f/1.4, Kodak Portra 400 film tone, then excludes plastic skin, robotic movement, stiff poses。

Common pitfalls:

• Styling is glossed over with just one line about nice clothes. If the outfit changes when the scene changes, name every item and add a line that it is the same in every scene.
• Cramming three actions into a three-second segment. One scene, one action; the Paris one does only one thing every three seconds.
• Handing the entire copy to the model for on-screen text. The only on-screen text in the Tokyo one is TOKYO、MADE TO BE SEEN short one- or two-line phrases like this; long blocks of text come out blurry when rendered, so leave them for post.
• Slow motion plus transition effects throughout. The fast-cut segment of the Tokyo one hard-codes hard cuts synchronized to the beat, and slow is reserved only for the final hero shot.

Copy-ready lead-in / 可复制引导语

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

I want a fashion lookbook clip. [The model is an Asian woman with short hair, walking through a plane-tree neighbourhood in Shanghai in autumn.] [The hero pieces are an oatmeal trench coat and a brown leather tote.] Using the prompt template below, rewrite it into one ready-to-use Seedance video prompt for me:

I want to make a fashion lookbook short film, [the model is an Asian girl with short hair, walking through the plane-tree streets of autumn Shanghai], [the hero product is an oatmeal-colored long trench coat with a brown leather tote bag]. Please use the prompt template below to help me rewrite it into a Seedance video prompt that can be used directly:

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.