by ristponex
π NSFW AI Image Generator β 30+ uncensored image models via Atlas Cloud API. Flux, Seedream, Ideogram & more. AI Agent Skill
# Add to your Claude Code skills
git clone https://github.com/ristponex/nsfw-ai-image-generator-skillGenerate uncensored AI images using Atlas Cloud API (30+ image models).
ATLAS_CLOUD_API_KEY environment variable set| Tool | Script | What It Does |
|------|--------|-------------|
| Image Generate | scripts/generate.py generate | Generate AI images from text prompts |
| List Models | scripts/generate.py models | List available image models on Atlas Cloud |
uv run scripts/generate.py generate "your prompt" --model flux-pro
uv run scripts/generate.py models
| Shortcut | Model ID |
|----------|---------|
| flux-pro | black-forest-labs/flux-2-pro |
| flux-schnell | black-forest-labs/flux-1.1-schnell |
| ideogram | ideogram-ai/ideogram-v3 |
| imagen | google/imagen-4-ultra |
| seedream | bytedance/seedream-v5.0 |
You can also pass any full model ID with --model.
Before calling this script, you MUST first use Atlas Cloud MCP tools:
atlas_list_models with type="Image" to see all available image modelsatlas_get_model_info with the chosen model ID to get its parameter schemaGenerate uncensored AI images with 30+ models β Flux, Seedream, Ideogram, Imagen & more
A Claude Code skill that generates uncensored NSFW AI images through the Atlas Cloud API. Access 30+ state-of-the-art image generation models β including Flux 2 Pro, Seedream V5, Ideogram V3, Imagen 4 Ultra, and more β without running local GPU hardware or dealing with complex setup.
No content filters, no prompt rewriting, no invisible safety classifiers silently modifying your output. You write the prompt, the model generates exactly what you describe.
Switch between Flux, Seedream, Ideogram, Imagen, HunyuanImage, and dozens more without managing separate accounts, API keys, or SDKs. One unified interface for all of them.
Flux Schnell starts at roughly $0.003 per image. No monthly subscriptions, no token packs, no minimum spend. You pay only for what you generate.
Built as a Claude Code skill. Your AI agent can discover models, check parameter schemas, and generate images autonomously β no human-in-the-loop required for the API calls.
No comments yet. Be the first to share your thoughts!
scripts/generate.py generate with the correct --model and parametersImages are generated server-side via API and delivered directly to you. No prompts are stored, no generated images are logged, no training on your data.
npx skills add ristponex/nsfw-ai-image-generator-skill
Sign up at Atlas Cloud to get a free API key. New accounts include free credits β no credit card required.
Mac / Linux:
export ATLAS_CLOUD_API_KEY=your_api_key_here
To persist across sessions, add the line above to your ~/.bashrc, ~/.zshrc, or ~/.profile.
Windows (PowerShell):
$env:ATLAS_CLOUD_API_KEY = "your_api_key_here"
Windows (CMD):
set ATLAS_CLOUD_API_KEY=your_api_key_here
Or use a .env file in the project root:
ATLAS_CLOUD_API_KEY=your_api_key_here
| Model | ID | Quality | Price |
|---|---|---|---|
| Flux 2 Pro | black-forest-labs/flux-2-pro | Best overall quality | ~$0.05/img |
| Flux Schnell | black-forest-labs/flux-1.1-schnell | Fast, budget-friendly | ~$0.003/img |
| Ideogram V3 | ideogram-ai/ideogram-v3 | Best text rendering | ~$0.04/img |
| Imagen 4 Ultra | google/imagen-4-ultra | Photorealistic | ~$0.08/img |
| Seedream V5 | bytedance/seedream-v5.0 | High detail, vibrant | ~$0.03/img |
These are the most popular models. Atlas Cloud offers 30+ image models total β run
uv run scripts/generate.py modelsor useatlas_list_modelsto see them all.
| Use Case | Recommended Model | Why | |---|---|---| | General high quality | Flux 2 Pro | Best balance of quality and speed | | Bulk generation on budget | Flux Schnell | $0.003/img, 2-3s per image | | Images with text/logos | Ideogram V3 | Industry-leading text rendering | | Photorealistic portraits | Imagen 4 Ultra | Google's best photorealism model | | Anime / illustration | Seedream V5 | Excellent at stylized content |
Once the skill is installed, simply ask Claude to generate images:
> Generate a fantasy landscape with dramatic lighting using Flux Pro
> Create a photorealistic portrait with Imagen 4 Ultra
> Generate 4 variations of a cyberpunk cityscape with Seedream
Claude will automatically:
atlas_list_modelsatlas_get_model_infoGenerate an image:
uv run scripts/generate.py generate "a surreal underwater city with bioluminescent architecture" --model flux-pro
Use a specific model ID:
uv run scripts/generate.py generate "portrait of a woman in golden hour light" --model black-forest-labs/flux-2-pro
Set image size:
uv run scripts/generate.py generate "wide cinematic landscape" --model flux-pro --size 1920x1080
Set aspect ratio:
uv run scripts/generate.py generate "vertical fashion photo" --model ideogram --aspect-ratio 9:16
Generate multiple images:
uv run scripts/generate.py generate "abstract art" --model flux-schnell --count 4
Custom output directory:
uv run scripts/generate.py generate "your prompt" --model flux-pro -o ./my-images
Pass extra model-specific parameters:
uv run scripts/generate.py generate "your prompt" --model flux-pro --extra '{"guidance_scale": 7.5}'
List all available models:
uv run scripts/generate.py models
For convenience, you can use short names instead of full model IDs:
| Shortcut | Full Model ID |
|---|---|
| flux-pro | black-forest-labs/flux-2-pro |
| flux-schnell | black-forest-labs/flux-1.1-schnell |
| ideogram | ideogram-ai/ideogram-v3 |
| imagen | google/imagen-4-ultra |
| seedream | bytedance/seedream-v5.0 |
| Platform | Flux Pro | Monthly Cost | NSFW Support | Notes | |---|---|---|---|---| | Atlas Cloud | ~$0.05/img | Pay per use | β Yes | 30+ models, no subscription | | Midjourney | N/A | $10β60/mo | β No | Subscription only, censored | | DALL-E 3 | ~$0.04/img | Pay per use | β No | Heavily censored | | Stable Diffusion (local) | Free | Need GPU ($500+) | β Yes | Requires setup & hardware | | RunwayML | N/A | $12β76/mo | β No | Focused on video | | Leonardo AI | N/A | $10β48/mo | β No | Limited free tier |
If you prefer running models on your own GPU, here are popular open-source options for uncensored image generation:
| Factor | Local (ComfyUI, etc.) | This Skill (Atlas Cloud) | |---|---|---| | Cost per image | Free (after GPU purchase) | $0.003β$0.08 | | Setup time | Hoursβdays | 2 minutes | | GPU required | Yes (8β24GB VRAM) | No | | Model updates | Manual download | Automatic | | Batch generation | Limited by VRAM | Unlimited | | Internet required | No (after setup) | Yes | | Claude Code integration | Manual | Built-in |
This skill is the easiest way to generate NSFW AI images β no GPU setup, no model downloads, no dependency hell. If you already have a powerful GPU and enjoy tinkering, the local options above are great. If you want results in 2 minutes, install this skill.
Dependencies (requests, pillow) are managed automatically by uv β no manual pip install needed.
nsfw-ai-image-generator-skill/
βββ SKILL.md # Skill metadata (used by Claude Code)
βββ scripts/
β βββ generate.py # Main generation script
βββ .env.example # Environment variable template
βββ LICENSE # MIT License
βββ README.md # This file
βββ README_zh.md # δΈζθ―΄ζ
βββ README_ja.md # ζ₯ζ¬θͺγγγ₯γ‘γ³γ
βββ README_ko.md # νκ΅μ΄ λ¬Έμ