adobe-firefly-image
Use Adobe Firefly Services to generate, edit, expand, fill, match, composite, and upscale still images through the current REST APIs. Apply when selecting Firefly Image 5 versus Image 3/4 or custom models, implementing authenticated asynchronous image workflows, using style or structure references, building product composites, handling provenance and enterprise rights, or diagnosing Firefly image jobs in production. Exclude Firefly video, audio, and unrelated Creative Cloud APIs.
Profile →npx skills add calesthio/generative-media-skills --skill adobe-firefly-image --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Treat this as a still-image production and integration skill. It directs an agent to use Adobe Firefly Services to generate, edit, expand, fill, match, composite, and upscale still images through the current REST APIs, with emphasis on Image 5 workflows, authenticated async processing, and handling provenance and enterprise rights.
How it works
- It defines a production-oriented workflow for Firefly Image tasks, excluding video, audio, and unrelated Creative Cloud ops.
- It documents the current API and model map for image generation and editing, including endpoints and model headers/identifiers (e.g., v4 for Image 5 generation with x-model-version: image5 and modelId: firefly_image; v3 for Image 3/4 generation; similar endpoints for generate-similar, fill, expand, object composites, precise/adaptive composites, and upscale).
- It specifies authentication: obtain an IMS token, then call API endpoints with Authorization: Bearer <token> and x-api-key set to the client ID; refresh tokens before expiry per guidance.
- It outlines request contracts for Image 5 (v4) and Image 3/4 (v3), including required fields (prompt, aspectRatio, resolutionLevel, modelId, numVariations, seeds, referenceBlobs) and how those fields influence operation (e.g., referenceBlobs switches to edit mode; omit aspectRatio when using reference blobs).
- It provides guidance on uploads (image/mask) and allowed source URLs, with a seven-day validity for IDs and notes on content caching.
- It describes composite and upscale workflows (Generate Object Composite, Precise Composite, Adaptive Composite, and upscale with precise_upsampler_v1), including when to use each and how results are returned asynchronously (status polling through provided URLs).
- It emphasizes style and structure controls via v3 style.imageReference and structure.imageReference, with guidance on tuning strengths and using a documented preset catalog.
- It advises on prompt construction, with a structured seven-point brief and cautions about rights, localization, and typography handling.
When to use it
- Use for choosing between Image 5 versus Image 3/4 or custom models, selecting authenticated async image workflows, applying style/structure references, building product composites, and handling provenance and rights.
- Use for diagnosing Firefly image jobs in production and ensuring compliance with enterprise rights and provenance requirements.
What it can touch
- API endpoints for image generation, edits, fills, expansions, composites, and upscaling as listed under the Current API and model map (e.g., POST /v4/images/generate-async, POST /v3/images/generate-async, POST /v3/images/fill-async, POST /v3/images/expand-async, POST /v3/images/upscale).
- Authentication mechanisms including OAuth token requests and headers Authorization: Bearer <access-token> and x-api-key: <client-id>.
- Upload storage endpoints such as POST /v2/storage/image for input images or masks.
- Status and result polling URLs provided by the API responses (statusUrl, links.result.href).
Caveats
- Documents production and API version conflicts; reconcile against the API reference, changelog, and usage notes before shipping.
- Image 5 uses v4 endpoints with fields like aspectRatio, resolutionLevel, modelId, modelSpecificPayload, referenceBlobs; do not send v3-only fields (style, structure, contentClass, visualIntensity, customModelId) to v4.
- Up-to-date authentication and entitlement are required; a 403 often indicates entitlement or policy issues rather than OAuth errors.
- Outputs are asynchronous; poll the result URL until terminal state and then download the image promptly.
# Adobe Firefly Image Treat this as a still-image production and integration skill. Keep video, audio, and unrelated Photoshop, Lightroom, Express, or Creative Production operations out of scope unless the user explicitly asks to combine systems. ## Evidence discipline Use these labels consistently: - **Documented** means the current Adobe API reference, changelog, product terms, or security mater
What does the adobe-firefly-image skill do?
Use Adobe Firefly Services to generate, edit, expand, fill, match, composite, and upscale still images through the current REST APIs. Apply when selecting Firefly Image 5 versus Image 3/4 or custom models, implementing authenticated asynchronous image workflows, using style or structure references, building product composites, handling provenance and enterprise rights, or diagnosing Firefly image jobs in production. Exclude Firefly video, audio, and unrelated Creative Cloud APIs.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill adobe-firefly-image --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.