git:20261027.947a93e to git:20261027.0e914e4

31 added, 36 removed. Audit A to A.

---

name: generate-image

description: Generate AI images for your Remotion project. Describe what you need — backgrounds, thumbnails, characters, abstract art — and get production-ready images via AI generation or Replicate models.

---

# Generate Image — AI Image Creation

You are helping the user generate custom images for their Remotion video project.

## Workflow

### 1. Understand the Need

Ask the user (if not already clear):

- **What is the image for?** — Scene background, thumbnail, character, product shot, abstract art, diagram?

- **Style** — Photorealistic, illustration, 3D render, flat design, watercolor, pixel art?

- **Dimensions** — Landscape (1920x1080), portrait (1080x1920), square (1080x1080)?

- **Mood/Colors** — Bright, dark, warm, cool, neon, pastel?

### 2. Craft the Prompt

- Write a detailed image generation prompt. Good prompts include:

- - Subject description

- - Art style

- - Lighting and mood

- - Camera angle/perspective

- - Color palette

- - Background details

+ Write the prompt in full sentences, following Replicate's official `prompt-images` skill for technique (it's model-agnostic, so it applies to KIE too). Cover, in order: subject, style, lighting, camera angle, color palette, background details.

**Good prompt examples:**

- - "Modern tech startup office, aerial view, clean minimalist design, bright natural lighting, white and blue color scheme, photorealistic"

- - "Abstract geometric pattern, dark background, glowing neon purple and blue lines, futuristic, 3D render"

- - "Friendly robot mascot waving, cartoon illustration style, pastel colors, clean white background, suitable for logo"

- - "Golden hour cityscape, drone aerial shot, warm orange and pink sky, downtown skyline silhouette, cinematic"

+ - "A modern tech startup office seen from above, clean minimalist design with white desks and blue accents, bright natural light from large windows, photorealistic."

+ - "An abstract geometric pattern of glowing neon purple and blue lines on a dark background, futuristic 3D render."

+ - "A friendly robot mascot waving, cartoon illustration with pastel colors on a clean white background, suitable for a logo."

+ - "A downtown skyline silhouetted against a warm orange and pink golden-hour sky, drone aerial shot, cinematic."

- ### 3. Generate via remotion-media

+ For a video, also:

+ - **Leave negative space** where Remotion will place titles or captions, and ask for "no text, no watermark"; Remotion renders the text.

+ - **Keep scenes consistent:** reuse one style block verbatim across every image in the video, and pass the first good image as a reference. See `skills/remotion-production/rules/image-generation.md`.

+ ### 3. Generate via remotion-media (default)

```

Use remotion-media generate_image:

- prompt: [crafted prompt]

- output_name: img-hero

- - aspect_ratio: 16:9 # match the composition (9:16 for shorts)

+ - aspect_ratio: 16:9 # always pass it (default is 1:1); 9:16 for shorts

+ - resolution: 2K # default 1K; use 2K+ for 1080p compositions

+ - image_urls: [optional reference images, up to 8, public URLs only]

```

- The image is saved to `public/` of the directory your agent was launched from, so start your agent (Claude Code, Codex, Gemini CLI…) from the Remotion project root.

+ The image is saved to `public/img-hero.png` in the directory your agent was launched from, so start your agent (Claude Code, Codex, Gemini CLI…) from the Remotion project root. Reference images in `image_urls` must be public URLs KIE can fetch, not files in `public/`.

- ### 4. Generate via Replicate MCP (if available)

+ ### 4. Generate via Replicate (specific models)

- If the user has `REPLICATE_API_TOKEN` set and wants more model options, use the Replicate MCP tools:

+ Use Replicate when the user wants a specific model (typography, several references, a particular look) or KIE fails. It needs the local `replicate-mcp` server with `REPLICATE_API_TOKEN`. Follow Replicate's official `find-models` and `run-models` skills:

- ```

- # FLUX for high-quality images

- replicate_run:

- model: "black-forest-labs/flux-1.1-pro"

- input:

- prompt: "[crafted prompt]"

- aspect_ratio: "16:9"

- output_format: "png"

- ```

+ 1. **Search, then read the schema.** `search_models` with `body: "<task>"`, then `get_models` (`model_owner`, `model_name`) and `list_models_examples`. Use only inputs that exist in the schema; the aspect-ratio input name varies per model.

+ 2. **Create the prediction.** Official models: `create_models_predictions` with `model_owner`, `model_name` and `input`. Community models: `create_predictions` with `version: "owner/name:<version_id>"`. Fast image models can take `Prefer: "wait"` (blocks up to 60 s).

+ 3. **Poll** `get_predictions` with `prediction_id` until `status` is `succeeded`, `failed` or `canceled`.

+ 4. **Download** the URL in `output` right away (it expires after 1 hour):

- Download the output to the project:

```bash

mkdir -p public/images

- curl -L -o public/images/img-[descriptive-name].png "[replicate_output_url]"

+ curl -L -o public/images/img-[descriptive-name].png "<output URL>"

```

- Available Replicate models:

- - **FLUX 1.1 Pro** (`black-forest-labs/flux-1.1-pro`) — High quality, great prompt following

- - **Imagen 4** (`google/imagen-4`) — Google's latest, photorealistic

- - **Ideogram v3** (`ideogram-ai/ideogram-v3`) — Best for text-in-image

- - **FLUX Kontext** (`black-forest-labs/flux-kontext-pro`) — Style control, multi-reference

+ Starting points, as of Oct 2026 (search and read the schema before calling):

+ - **FLUX.2 Pro / Max** (`black-forest-labs/flux-2-pro`, `-max`): photoreal, several reference images via `input_images`

+ - **Nano Banana Pro** (`google/nano-banana-pro`): image with text, editing

+ - **GPT Image 2** (`openai/gpt-image-2`)

+ - **Ideogram v3 Quality / Turbo** (owner `ideogram-ai`, one ID per tier; search `ideogram`): typography, logos

+ - **FLUX Kontext Pro** (`black-forest-labs/flux-kontext-pro`): edit from a single reference (`input_image`)

- See `skills/remotion-production/rules/replicate-models.md` and `rules/image-generation.md` for detailed prompt engineering and model selection guidance.

+ See `skills/remotion-production/rules/replicate-models.md` for the full flow and `rules/image-generation.md` for provider choice and consistency guidance.

### 5. Show Usage in Remotion

Add the image with `<CanvasImage>` from `remotion`, as the official `remotion-markup` skill does (`<Img>` still works; both accept `effects`). Sizing and animation follow its images.md and timing.md. The path depends on the provider: `generate_image` saves to `public/<output_name>.png`, Replicate downloads to `public/images/`.

```tsx

import { CanvasImage, Easing, interpolate, staticFile, useCurrentFrame, useVideoConfig } from "remotion";

const frame = useCurrentFrame();

const { fps } = useVideoConfig();

// As a background (remotion-media output)

<CanvasImage

src={staticFile("img-hero.png")}

style={{ width: "100%", height: "100%", objectFit: "cover" }}

// As an element that pops in (Replicate download)

<CanvasImage

src={staticFile("images/img-product.png")}

style={{

scale: interpolate(frame, [0, 0.6 * fps], [0, 1], {

extrapolateLeft: "clamp", extrapolateRight: "clamp",

easing: Easing.spring({ damping: 200 }),

output: "perceptual-scale",

}),

}}

```

For a slow Ken Burns move on a still, see `skills/remotion-production/rules/image-generation.md`.

### 6. Iterate

If the image isn't right:

- - Adjust the prompt — be more specific about what's wrong

- - Try a different style descriptor

+ - Adjust the prompt — be more specific about what's wrong (see `prompt-images` for editing and common pitfalls)

- Generate multiple variations and let the user pick

- - Use negative prompts if the model supports them ("no text, no watermark")

+ - Use exclusions only if the model supports them ("no text, no watermark"); some models get worse with negative prompts

+ - Change one thing at a time so the image still matches the other scenes