by ristponex
🎨 Seedream image generation skill — batch, editing, text rendering. Claude Code & 15+ platforms.
# Add to your Claude Code skills
git clone https://github.com/ristponex/seedream-image-skillThis project provides a CLI tool (seedream) for generating and editing images using ByteDance's Seedream models via the Atlas Cloud API.
seedream "your prompt here"
seedream "edit instructions" --mode edit --image ./source.png --strength 0.75
seedream "replace area" --mode edit --image ./source.png --mask ./mask.png
seedream "prompt" --mode batch --count 5
seedream "prompt" --nsfw
--model v5.0-lite (default) — Latest, fastest--model v4.5 — Previous generation--model v4 — Cost-effective--size WxH — Image dimensions (default: 1024x1024)--steps N — Inference steps (default: 25)--guidance N — Guidance scale (default: 5.0)--seed N — Random seed--output path — Custom output path--negative-prompt "text" — Negative promptImages are saved to ./output/ directory by default.
Requires ATLAS_CLOUD_API_KEY in .env file.
An AI Agent Skill for generating and editing images using ByteDance's Seedream models via Atlas Cloud API.
Works with 15+ AI coding agents including Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Windsurf, OpenCode, Kiro, and more.
Seedream is ByteDance's state-of-the-art image generation model family, renowned for its exceptional Chinese text rendering, typography, and poster design capabilities. This skill brings Seedream's power directly into your AI coding workflow.
| Model | ID | Starting Price per Image | Description |
|-------|-----|--------------------------|-------------|
| Seedream v5.0 Lite | bytedance/seedream-v5.0-lite | from $0.032/image | Latest generation, fast and high quality |
| Seedream v5.0 Lite Edit | bytedance/seedream-v5.0-lite/edit | from $0.032/image | Image editing with v5.0 Lite |
| Seedream v5.0 Lite Sequential | bytedance/seedream-v5.0-lite/sequential | from $0.032/image | Batch generation up to 15 images |
| Seedream v5.0 Lite Edit Sequential | | from $0.032/image | Batch editing up to 15 images |
| Seedream v4.5 | | from $0.030/image | Previous generation, proven quality |
| Seedream v4.5 Edit | | from $0.030/image | Image editing with v4.5 |
| Seedream v4.5 Sequential | | from $0.030/image | Batch generation with v4.5 |
| Seedream v4 | | from $0.028/image | Stable, cost-effective option |
No comments yet. Be the first to share your thoughts!
bytedance/seedream-v5.0-lite/edit-sequentialbytedance/seedream-v4.5bytedance/seedream-v4.5/editbytedance/seedream-v4.5/sequentialbytedance/seedream-v4Prices shown are starting prices. Higher resolution or additional features may cost more.
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| prompt | string | (required) | Text description of the desired image |
| size | string | 1024x1024 | Output image dimensions (e.g., 512x512, 1024x1024, 1280x720) |
| num_inference_steps | number | 25 | Number of denoising steps (higher = better quality, slower) |
| seed | number | random | Random seed for reproducible results |
| guidance_scale | number | 5.0 | How closely to follow the prompt (higher = more faithful) |
| num_images | number | 1 | Number of images to generate (1 for standard, up to 15 for sequential) |
| negative_prompt | string | — | What to avoid in the generated image |
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| prompt | string | (required) | Text description of the desired edit |
| image | string | (required) | Base64-encoded image or URL of the source image |
| mask_image | string | — | Base64-encoded mask or URL (white = edit area, black = preserve) |
| strength | number | 0.75 | Edit strength (0.0 = no change, 1.0 = full regeneration) |
| size | string | from source | Output image dimensions |
| num_inference_steps | number | 25 | Number of denoising steps |
| seed | number | random | Random seed for reproducible results |
| guidance_scale | number | 5.0 | How closely to follow the prompt |
| negative_prompt | string | — | What to avoid in the edit |
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| prompt | string | (required) | Text description for the batch |
| num_images | number | (required) | Number of images to generate (up to 15) |
| size | string | 1024x1024 | Output image dimensions |
| num_inference_steps | number | 25 | Number of denoising steps |
| seed | number | random | Base random seed |
| guidance_scale | number | 5.0 | How closely to follow the prompt |
| negative_prompt | string | — | What to avoid in the generated images |
Seedream is the undisputed leader in rendering Chinese characters within generated images. Whether you're creating posters, banners, social media graphics, or product mockups with Chinese typography, Seedream produces crisp, accurate, and beautifully styled text that other models simply cannot match.
The Seedream model family has been specifically optimized for commercial design use cases:
Atlas Cloud provides whitelisted access to Seedream's full capabilities, including NSFW content generation. This is ideal for:
Need a series of related images? Seedream's sequential mode generates up to 15 coherent, thematically linked images in a single API call — perfect for:
# Clone the repository
git clone https://github.com/thoughtincode/seedream-image-skill.git
cd seedream-image-skill
# Install dependencies
bun install
# Set up your API key
cp .env.example .env
# Edit .env and add your ATLAS_CLOUD_API_KEY
# Link the CLI globally
bun link
seedream --help
seedream "A majestic dragon flying over a mountain range at sunset"
seedream "Cyberpunk cityscape at night" --model v4.5 --size 1280x720
seedream "Add a rainbow in the sky" --mode edit --image ./photo.png --strength 0.6
seedream "Replace with a red sports car" --mode edit --image ./scene.png --mask ./mask.png
seedream "Cute cat in different poses" --mode batch --count 5
seedream "Comic panels of a space adventure" --mode batch --count 8 --size 768x768 --steps 30
seedream "Artistic figure study, oil painting style" --nsfw
seedream "A beautiful Japanese garden in autumn" \
--model v5.0-lite \
--size 1024x1024 \
--steps 30 \
--guidance 7.5 \
--seed 42 \
--output ./my-garden.png \
--negative-prompt "blurry, low quality"
seedream <prompt> [options]
Arguments:
prompt Text description of the image to generate
Options:
--model <variant> Model variant: v5.0-lite (default), v4.5, v4
--mode <mode> Generation mode: generate (default), edit, batch
--size <WxH> Image dimensions (default: 1024x1024)
--steps <n> Inference steps (default: 25)
--guidance <n> Guidance scale (default: 5.0)
--count <n> Number of images for batch mode (default: 1, max: 15)
--seed <n> Random seed for reproducibility
--output <path> Output file path (default: ./output/<timestamp>.png)
--image <path> Source image for edit mode (file path or URL)
--mask <path> Mask image for edit mode (file path or URL)
--strength <n> Edit strength 0.0-1.0 (default: 0.75)
--negative-prompt <text> What to avoid in the generation
--nsfw Enable NSFW content generation
--help Show this help message
This tool is designed to work as an AI agent skill across all major coding agents. Install it with a single command:
npx skills add seedream-image-skill
This works with Claude Code, Cursor, OpenAI Codex, GitHub Copilot, Gemini CLI, Windsurf, OpenCode, Kiro, and any agent that supports skill installation.
## Image Generation with Seedream
Use the `seedream` CLI to generate images:
- Basic: `seedream "your prompt here"`
- Edit: `seedream "edit instructions" --mode edit --image ./source.png`
- Batch: `seedream "prompt" --mode batch --count 5`
- NSFW: add `--nsfw` flag
- Models: v5.0-lite (default), v4.5, v4
seedream CLI./output directorySet your Atlas Cloud API key in the .env file or as an environment variable:
export ATLAS_CLOUD_API_KEY=your_api_key_here
| Endpoint | Method | Description |
|----------|--------|-------------|
| https://api.atlascloud.ai/api/v1/model/generateImage | POST | Submit image generation request |
| `https