Story Frame Continuation · সর্বজনীন Open Skill

Story Frame Continuation

Story Frame Continuation Digen-এ একটি সর্বজনীন Open Skill। খুলে দেখুন এই ওয়ার্কফ্লো কী তৈরি করে।

@MiraScenes

Story

1 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321757/2026-10-22/zbjasrv8.webp

# Story Frame Continuation

The next beat of the story, drawn in the same hand. Your existing frame stays the visual anchor — same characters, same palette, same linework — while one new moment unfolds in it.

## When to use

- The user wants the next frame of their story drawn from an existing image with the same characters and style (continue the story image, next panel of my scene, extend my illustration)
- A variation on a previous result: quiet exchange

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 |
| Description | Yes | — | What the user wants; merged into the prompt |
| Beat | No | `stepping into a new place` | stepping into a new place (default), quiet exchange, dramatic turn, or user-described next moment |
| Mood | No | `wonder and discovery` | wonder and discovery (default), tense anticipation, warmth and reunion, or user-described |
| Framing | No | `cinematic medium shot` | cinematic medium shot (default), wide establishing shot, close two-shot |
| Ratio | No | `3:4 default` | 3:4 default; 2:3, 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='Story Frame Continuation', 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. "Here it is: your story frame continuation. Shall I do a version with quiet exchange?" Results appear on the canvas; never paste URLs.

## Prompt templates

**PROMPT**

```text
<if photo: The same adult from the reference: <identity line>.> Intentional changes: one new story frame in the exact style of the source frame kept intact (same medium, linework, palette, rendering finish, character designs and outfits), showing the same adult characters with identical faces, hair and clothing in <beat: stepping together into a new place (default), a quiet exchange in the same world, a dramatic turn, or a user-described next moment>, <mood: wonder and discovery (default), tense anticipation, warmth and reunion, or user-described>, cinematic layered composition with real depth, light native to the established world, fully clothed, non-explicit, no panel borders or lettering. <user details and options>. Apply the style to the entire frame with its signature traits (medium, texture, palette, linework); the person stays recognizable under the style. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested.
```

Quality bar: Name the style's visual traits (medium, brushwork or render, palette, line