Consistent Character Scene Reel · öffentlicher Open Skill

Consistent Character Scene Reel

Consistent Character Scene Reel ist ein öffentlicher Open Skill auf Digen. Öffne ihn, um zu sehen, was dieser Workflow erstellt.

@SkateSkye

Custom

1 0 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321670/2026-10-22/9eavxyzc.webp

# Consistent Character Scene Reel

One face, endless scenes. The same character — same features, hair and vibe — is placed into whatever scenario you describe, in a soft real or illustrated look.

## When to use

- The user wants their character kept consistent while posing them in a new scene or scenario (consistent character shot, chat log to scene, character scenario edit)
- A variation on a previous result: city street at golden hour

Not for: Video output (use a video skill).

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Person photo | No | — | Optional; if given, the face is preserved |
| Character reference | No | — | an extra face or outfit image for consistency |
| Description | Yes | — | What the user wants; merged into the prompt |
| Scenario | No | `sunlit café corner` | sunlit café corner (default), city street at golden hour, beach boardwalk, cozy study, or user-described |
| Outfit | No | `source outfit` | source outfit (default), oversized knit sweater, leather jacket, or user-described |
| Framing | No | `three-quarter torso` | three-quarter torso (default), full body, waist-up |
| Mood | No | `warm and candid` | warm and candid (default), cool and aloof, joyful |
| Look | No | `clean real-photo` | clean real-photo (default), soft illustrated |
| Ratio | No | `3:4 default` | 3:4 default; 1:1, 9:16, 16:9 on request |

- If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use.
- Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors.

## Steps

1. Read `references/image-edit.md` for prompt structure.
2. Fill the template below from the user's description. Use the tuned defaults for anything they leave out; ask one short question only if the subject itself is unclear.
3. If a person photo is given: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')` and add the identity clause.
4. With reference images: `generate_image(prompt=<PROMPT>, input_urls=[refs...], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Consistent Character Scene Reel', entity_type='skill_generation')`; without: the same call with `model='t2i.hd'` and no `input_urls`.
5. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely.
6. Reply in one or two sentences, e.g. "All set. Your consistent character scene reel is on the canvas. Next I can do city street at golden hour." Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
<if photo: The same adult from the reference: <identity line>.> Intentional changes: the same adult character from the reference (keep face shape, eyes, nose, hair color and length, body proportions and the source medium, real or anime) in <scenario: a sunlit café corner (default), city street at golden hour, beach boardwalk, cozy study or user-described>, wearing <outfit: the source outfit (default), an oversized knit sweater, a leather jacket, or user-described>, relaxed natural pose, camera at <framing: three-quarter torso (default), full body, waist-up>, <mood: warm and candid (default), cool and aloof, joyful>, soft directional light, shallow depth of field, detailed background with depth, fully clothed, tasteful. <user details and options>. Professional composition, deliberate lens and light, rich environmental detail. Lighting and materials described concretely; composition suited t