Run any Skill in Manus with one click

cf-image

Stars56

Forks44

UpdatedJuly 9, 2026 at 10:11

Generate an image from a text description using Cloudflare Workers AI (the flux-1-schnell model). Use this skill whenever the user wants to create, generate, make, or draw an image / picture / logo / icon / thumbnail / wallpaper / banner from a text idea and mentions Cloudflare, or is working in this repo and asks for a quick generated image. Claude expands the user's request into a strong image prompt, runs the bundled generate.py, and saves a JPG to disk. Trigger on phrases like "generate an image of", "make me a picture of", "create a thumbnail for", "cloudflare image", or a plain description paired with a request for an image. Requires CF_ACCOUNT_ID and CF_API_TOKEN in the project's .env.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

hassancs91

hassancs91/claude-image-generation

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

2 files

SKILL.md

readonly

name

cf-image

description

cf-image

Turn a natural-language request into a generated image using Cloudflare Workers AI (@cf/black-forest-labs/flux-1-schnell). This skill is the "connect Claude to image generation" loop: the user describes what they want, Claude does the prompt engineering, the bundled script calls the Cloudflare API, and the image is saved locally.

When this skill applies

The user wants an image generated from a description — e.g. "generate a logo idea for a coffee shop", "make a thumbnail for my AI video", "picture of a cyberpunk cat". Claude is responsible for turning a vague ask into a good prompt before generating.

It does not apply to: editing an existing image, vector/SVG art, or video.

How to run it

From the repo root:

python .claude/skills/level-3-image-generator/generate.py "<optimized prompt>" -o <filename>.jpg

"<optimized prompt>" — the prompt you write (see below), not the user's raw words.
-o / --output — where to save (default out.jpg). Pick a short descriptive name, e.g. coffee-logo.jpg.
--steps — diffusion steps (default 4). flux-schnell is tuned for few steps; 4–8 is plenty. Higher is slower, not always better.

The script prints Saved <file> ... on success, or a Cloudflare API error message on failure.

The one job Claude must do: write a strong prompt

The raw script would need a hand-written prompt. The value of this skill is that Claude expands the user's intent into a vivid, specific prompt before calling the script. A good Flux prompt names:

Subject — what's in the frame, concretely.
Style/medium — photo, 3D render, flat vector, watercolor, isometric, etc.
Composition & framing — close-up, wide shot, centered, rule-of-thirds.
Lighting & mood — golden hour, neon, soft studio light, dramatic shadows.
Color/detail cues — palette, background, level of detail.

Example transformation:

User: "a logo for a coffee shop"
Prompt you pass: "minimalist logo of a steaming coffee cup, flat vector illustration, warm brown and cream palette, centered on a clean off-white background, simple bold shapes, modern branding"

Keep prompts to one or two sentences. Don't include text/words to render — Flux is unreliable at rendering legible text.

After generating

Confirm the file was saved (the script prints the path).
Tell the user the filename and the exact prompt you used, so they can tweak and re-run.
If they want variations, re-run with a modified prompt and a new -o filename.

Requirements

CF_ACCOUNT_ID and CF_API_TOKEN set in the project's .env (see .env.example). The script loads them automatically.
Python deps: requests, python-dotenv.

More from this repository

same repository

prompt-to-design

hassancs91/claude-image-generation

Generate a polished PNG graphic from a text prompt and an aspect ratio. This is a CODE-BASED design generator (not a diffusion/photo model): it builds images from gradients, mesh fields, glow, grain, geometric shapes, and real typography. Use it whenever the user wants to create / generate / make an "image", poster, cover, wallpaper, banner, thumbnail, album art, story or reel cover, quote card, or any graphic from a description — optionally with words to render and a size or ratio (e.g. 1:1, 4:5, 9:16, 16:9, 2:3, 1:2, or WxH). It excels at designed, typographic, abstract, gradient, and geometric/Bauhaus/Swiss graphics and soft product-style visuals. It CANNOT produce photorealistic photos, real named people, brand logos, or copyrighted characters — for those, translate intent into a strong designed/stylized take instead.

2026-07-0956

3d-image-renderer

hassancs91/claude-image-generation

Generate PNG images by building a real Three.js 3D scene and capturing one frame headlessly — no image model involved. Takes a text prompt and an aspect ratio (1:1, 16:9, or 9:16) and produces a rendered PNG. Use this skill whenever the user asks to generate, create, or render an image, picture, scene, wallpaper, thumbnail background, or product shot with this system — especially with phrases like "generate an image of", "render a scene", "create a PNG", "no image model", "3D render of", or a prompt paired with an aspect ratio. Also use it when the user wants an image in a named visual style (dark studio, Apple light, nature, sunset, night, underwater). Not for editing existing images, 2D vector art, or animated video (VidTSX handles video).

2026-07-0956

scene-splitter

hassancs91/claude-image-generation

Splits a plain English story into a numbered list of SCENES — each scene being one moment that gets exactly one illustration AND one narration clip downstream. The first step of the AI Storybook pipeline. Tuned for beginner-level stories (short sentences, ~8-12 scenes), with a per-scene length cap so each scene fits one phone screen without scrolling. Use this skill whenever the user wants to split a story into scenes, prepare a story for the storybook pipeline, break a story into pages/panels, or produce a scenes spine for the illustrator and narrator. Trigger on phrases like "split this story into scenes", "break this into pages", "prepare this story for the storybook", "make scenes for illustration", or whenever the user provides an English story and wants it chunked for a picture-book pipeline. Outputs a {slug}_scenes.json file consumed by the story-illustrator and story-narrator so they produce aligned output (1 image + 1 audio per scene).

2026-07-0956

story-html-publisher

hassancs91/claude-image-generation

Final step of the AI Storybook pipeline. Consolidates the scenes, images, and per-scene audio into ONE self-contained HTML storybook — a swipe/tap player with every image and audio clip embedded as base64 so the single file works offline and can be shared as-is. Reads {slug}_scenes.json, {slug}_images.json, and {slug}_audio/, then writes {slug}_story.json and {slug}.html. Use this skill whenever the user wants to build the final storybook, export to HTML, package the story, make the storybook file, generate the HTML, or wrap up the pipeline. Trigger on phrases like "build the storybook HTML", "export to HTML", "make the final file", "package the storybook", "generate the storybook", "wrap up the pipeline", or whenever the scenes + images + audio all exist and the user wants the single shareable file. Produces a single self-contained .html (images + audio embedded).

2026-07-0956

story-illustrator

hassancs91/claude-image-generation

Generates a consistent illustrated image for every scene of a story — keeping characters, locations, and visual style coherent across the whole sequence using cascading reference images. Reads a {slug}_scenes.json (from scene-splitter), proposes a visual style, ASKS the user for the aspect ratio and image model, extracts a visual bible, drafts a continuity-classified shot list, generates one reference image per character + location, then one image per scene (with a strict no-text/no-border constraint), and records every image in {slug}_images.json. Images are generated through the Fal API via the bundled fal_image.py script, with a pluggable model registry (nano-banana-2, nano-banana-pro, seedream-4, or any Fal model you add). Use this skill whenever the user wants to illustrate a story, generate scene images, draw the pictures for a storybook, build the illustrations, or produce a consistent visual sequence. Trigger on phrases like "illustrate this story", "generate the images", "draw the scenes", "make the

2026-07-0956

story-narrator

hassancs91/claude-image-generation

Generates one expressive narration MP3 per scene for an English storybook, using the ElevenLabs MCP (text_to_speech). Reads {slug}_scenes.json (from scene-splitter), proposes a warm storyteller voice, drafts the narration text per scene (optionally with Eleven v3 audio tags for emotion), lets the user review, then generates one MP3 per scene saved as {slug}_part_NN.mp3 so it pairs by index with the scene's image. Use this skill whenever the user wants to narrate a story, generate per-scene audio, voice a storybook, create read-along narration, or produce TTS for the storybook pipeline. Trigger on phrases like "narrate this story", "generate the audio", "voice the storybook", "make the narration", "read this story aloud", or whenever scenes.json exists and the user wants spoken audio. Requires the ElevenLabs MCP connected.

2026-07-0956

name

cf-image

description

cf-image

When this skill applies

It does not apply to: editing an existing image, vector/SVG art, or video.

How to run it

From the repo root:

python .claude/skills/level-3-image-generator/generate.py "<optimized prompt>" -o <filename>.jpg

"<optimized prompt>" — the prompt you write (see below), not the user's raw words.
-o / --output — where to save (default out.jpg). Pick a short descriptive name, e.g. coffee-logo.jpg.
--steps — diffusion steps (default 4). flux-schnell is tuned for few steps; 4–8 is plenty. Higher is slower, not always better.

The script prints Saved <file> ... on success, or a Cloudflare API error message on failure.

The one job Claude must do: write a strong prompt

Subject — what's in the frame, concretely.
Style/medium — photo, 3D render, flat vector, watercolor, isometric, etc.
Composition & framing — close-up, wide shot, centered, rule-of-thirds.
Lighting & mood — golden hour, neon, soft studio light, dramatic shadows.
Color/detail cues — palette, background, level of detail.

Example transformation:

User: "a logo for a coffee shop"
Prompt you pass: "minimalist logo of a steaming coffee cup, flat vector illustration, warm brown and cream palette, centered on a clean off-white background, simple bold shapes, modern branding"

Keep prompts to one or two sentences. Don't include text/words to render — Flux is unreliable at rendering legible text.

After generating

Confirm the file was saved (the script prints the path).
Tell the user the filename and the exact prompt you used, so they can tweak and re-run.
If they want variations, re-run with a modified prompt and a new -o filename.

Requirements

CF_ACCOUNT_ID and CF_API_TOKEN set in the project's .env (see .env.example). The script loads them automatically.
Python deps: requests, python-dotenv.