gooseworks-ai/goose-skills / skills/video/create-image-gpt-image-fal
create-image-gpt-image-fal
VerifiedGenerate a single photoreal or designed image with OpenAI gpt-image via fal.ai. Supports gpt-image-1 (default, fixed sizes — the FAL fallback for Higgsfield's `gpt_image_2`) and gpt-image-2 (`openai/gpt-image-2`, custom output sizes up to 3840px). Routes to text-to-image or the edit variant depending on whether a reference image is provided. Use for photoreal character anchors, scene keyframes, and designed sheets (e.g. storyboards) where precise layout and legible text matter.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 9.4 KB |
| scripts/generate.py | script | 6.9 KB |
| scripts/media_proxy.py | script | 56.8 KB |
| skill.meta.json | config | 155 B |
| tests/expected-output.md | markdown | 900 B |
| tests/human-test.md | markdown | 1.2 KB |
| tests/sample-input.md | markdown | 525 B |
| tests/smoke-test.md | markdown | 1.4 KB |
tests/expected-output.md
View on GitHub# Expected Output — create-image-gpt-image-fal
A correct run produces, per generation:
- A PNG at the requested `--output` path, > 1 KB, that opens as a valid image.
- A `<output>.meta.json` sidecar containing:
- `gateway: "fal"`
- `model` — the resolved fal endpoint (`fal-ai/gpt-image-1/text-to-image` or `openai/gpt-image-2`, plus `/edit` variants when a ref image is used)
- `model_family` — `gpt-image-1` or `gpt-image-2`
- `image_size`, `quality`, `prompt`, `cost_estimate_usd`
Model-specific:
- **gpt-image-1** — output is one of its fixed sizes (1024×1024, 1024×1536, 1536×1024); a custom `--image-size` is ignored with a warning.
- **gpt-image-2** — output matches the requested custom `--image-size` (rounded to a multiple of 16, capped at 3840px).
Image content is non-deterministic — judged on "valid image that plausibly matches the prompt", not exact pixels.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |