見出し、例、コード、表、リンク、参照画像を含む原文を表示しています。
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.
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", "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 | gpt-image-2 |
| Image-to-image with references, high-resolution refinement, broad aspect ratios | 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_extractwith the URL → returns brand colors, fonts,
personality/tone, and saved image files (logo, favicon, og_image).
- Optionally
firecrawl_urls_scrapewithformats=["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_ratioto intent (social, print, web). - Use
quality="high"for production,"draft"/"standard"while iterating. - Generated
file_ids can be reused asreference_imagesin later calls. - For website brand work, call
firecrawl_branding_extractbefore generating.

