image-generation

Image Generation

Generate images with the images_generate tool. It handles text-to-image, image-to-image (pass reference_images), and multi-image composition. By default (model="auto") it picks the best model for the request; set model to choose one.

Requirements

This skill assumes the Hyper MCP is connected to your agent so the images_generate tool is available. For brand-consistent ad creative work, Firecrawl must also be configured under your Hyper integrations.

How to run the tools in this skill

Every tool in this skill is named by its canonical tool name. Run it with the call your surface gives you:

Surface	Find a tool	Run it
MCP client (Claude, Cursor, Codex, ChatGPT)	`search("<what you want to do>")`, then `describe("<name>")`	`call("<name>", {...})`
Hyper CLI	`hyperai search "<what you want to do>"`, then `hyperai describe <name>`	`hyperai call <name> --json '{...}'`

If a tool is not found, its integration is not connected or not enabled for the workspace: stop and tell the user which integration to connect.

Call shape

images_generate(
    requests=[{"id": "ad1", "prompt": "A polished SaaS ad, clean composition"}],
    aspect_ratio="16:9",     # "1:1" (default), "9:16", "16:9", "4:5", "5:4", "2:3", "3:2", "3:4", "4:3", "21:9"
    quality="standard",      # "draft" | "standard" | "high"
    n=1,                      # 1-4 images per request
    model="auto",            # see "Choosing a model" below
)

Image-to-image / brand references: put files in the request: requests=[{"prompt": "Compose into a gift basket", "reference_images": ["file1", "file2"]}].
Reproducible output: pass seed=....
Ground in real-world search: pass use_search=True.
Do not display image URLs — they render automatically in chat.

Choosing a model

model="auto" is the right default. Override only when the task clearly calls for a specific model:

Task	`model`
First-pass concepts / quick ad ideation / everyday generation	`gpt-image-2.5-flare`
Precise edits and branded compositions from reference images, production creative	`gpt-image-2.5-sunburst`
Cheap iteration, image-to-image, the widest aspect ratios (adds 1:4, 1:8, 4:1, 8:1)	`nano-banana`
Readable text inside the image (posters, labels, infographics) or search-grounded scenes	`nano-banana-pro`
Product photography, material/fabric fidelity, accurate spatial depth	`seedream-4.5`

See references/image-prompting.md for per-model prompt-writing tips.

Branded / website ad creatives — extract branding first

If the user gives a website URL and wants on-brand creatives:

Call firecrawl_branding_extract with the URL → returns brand colors, fonts, personality/tone, and saved image files (logo, favicon, og_image).
Optionally firecrawl_urls_scrape with formats=["screenshot"] for visual context.
Write the prompt using the actual hex colors, font names, and tone, and pass the logo file_id in reference_images.

The branding result's file field is a JSON data file, NOT an image — never pass it as a reference. Only logo.file_id and images.*.file_id are usable images.

Higher-level workflows

For multi-shot product or marketplace work, prefer the workflow tools — they preserve product identity and return structured results:

images_product_photoshoots_create — multi-shot product photography (studio, lifestyle, hero, carousel, ad pack). See references/product-photoshoot.md.
images_marketplace_cards_create — marketplace listing image sets (Amazon main + secondary, A+ modules, Shopify). See references/marketplace-cards.md.

Reminders

Do NOT display image URLs to the user — they show automatically in chat.
Refine vague prompts unless the user wants verbatim generation.
Match aspect_ratio to intent (social, print, web).
Use quality="high" for production, "draft"/"standard" while iterating.
Generated file_ids can be reused as reference_images in later calls.
For website brand work, call firecrawl_branding_extract before generating.