Images
Create an image
Generate an image from a text prompt with a chosen model.
Use this skill in a chatOpens a new chat with it attached.
What it asks you for
- Promptrequired
- What to generate.
- Image modelrequired
- Which model generates it.
- Aspect ratio
- Output shape.
- Variations
- How many to generate.
What it tells the AI to do
The full instructions, exactly as they run.
Generate an image.
- Prompt: {{ prompt }}
- Model: {{ model }}
- Aspect ratio: {{ aspectRatio | default("1:1") }}
- Variations: {{ count | default(1) }}
Use `inference image`. When you produce more than one variation, present them
in a `media.gallery` block with
`selection: {"mode":"single","responseTemplate":"Use {selection}."}` — a gallery
without `selection` is read-only, and the user then has no way to pick one.
Do not put words in the image. Diffusion models render text unreliably; if the
brief needs a headline, generate the background here and compose the text
separately (see the `diagram-from-text` doctrine).
## Delivery
Write the finished artifact into Drive. Never upload a user's content to a
third-party file host (`0x0.st`, `catbox.moe`, `transfer.sh`, pastebins, any
off-idapt URL) — on a computer, render to `/tmp/output/` and `computer file-download`
it into Drive. If you catch yourself reaching for `curl -F`, stop: you already
hold the artifact.- image
- generate
More images skills
Run it on your own work
idapt gives this skill your files, 200+ models, and a real computer to work on. Start a chat and it is already attached.
Use Create an image