bytedance avatar

Image Generation

This is Claude's interface to an image generation service that works through structured JSON prompts. You describe what you want in a detailed schema (character features, lighting, composition, style references) and it calls a Python script to generate the image. It supports reference images, so you can feed in visual examples and have the prompt reference them directly, which is useful for things like "make this person look like Image 1 but in a Star Wars setting with a vehicle like Image 2." The workflow is a bit verbose with all the JSON structure, but that granularity means you can be specific about things like era, color palette, and negative prompts. Works for characters, scenes, products, whatever needs visualization.

skills.sh installs
2.9K
GitHub stars
85.2K
last updated
Aug 21, 2026

Install

$ npx -y skills add bytedance/deer-flow --skill image-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

Image Generation Skill

Overview

This skill generates high-quality images using structured prompts and a Python script. The workflow includes creating JSON-formatted prompts and executing image generation with optional reference images.

Core Capabilities

  • Create structured JSON prompts for AIGC image generation
  • Support multiple reference images for style/composition guidance
  • Generate images through automated Python script execution
  • Handle various image generation scenarios (character design, scenes, products, etc.)

Workflow

Step 1: Understand Requirements

When a user requests image generation, identify:

  • Subject/content: What should be in the image
  • Style preferences: Art style, mood, color palette
  • Technical specs: Aspect ratio, composition, lighting
  • Reference images: Any images to guide generation
  • You don't need to check the folder under /mnt/user-data

Step 2: Create Structured Prompt

Generate a structured JSON file in /mnt/user-data/workspace/ with naming pattern: {descriptive-name}.json

Step 3: Execute Generation

Sponsors

Details

Repository
github.com/bytedance/deer-flow
Categories
Design & UI/UX, Generative Media
First seen
May 16, 2026

More from bytedance/deer-flow

All 21
1adithya-s-k avatarmanim-composeradithya-s-k/manim_skillTrigger when: (1) User wants to create an educational/explainer video, (2) User has a vague concept they want visualized, (3) User mentions "3b1b style" or "exp2.9Kskills.sh installs
2web-infra-dev avatarcomputer-automationweb-infra-dev/midscene-skillsVision-driven desktop automation using Midscene. Control your local desktop (macOS, Windows, Linux) or a remote Windows desktop over RDP with natural language c2.8Kskills.sh installs
3agricidaniel avatarblog-chartagricidaniel/claude-blogGenerate dark-mode-compatible inline SVG data visualization charts for blog posts. Supports horizontal bar, grouped bar, donut, line, lollipop, area, and radar 2.7Kskills.sh installs
4owl-listener avatardata-visualizationowl-listener/designer-skillsDesign clear, accessible data visualizations with appropriate chart selection and styling.2.6Kskills.sh installs
5vladmdgolam avatarblender-mcpvladmdgolam/agent-skillsBlender MCP expert for scene inspection, Python scripting, GLTF export, and material/animation extraction. Activate when: (1) using Blender MCP tools (get_scene2.5Kskills.sh installs
6owl-listener avatarloading-statesowl-listener/designer-skillsDesign loading, skeleton, and progressive content reveal patterns.2.5Kskills.sh installs