NSFW Image Generation — Unrestricted AI Image Models

Generate AI images for mature creative projects using Wan 2.6, Seedream, and other models with relaxed content policies via Atlas Cloud API. Designed for adu...

Security Scan

The skill is mostly what it says (NSFW image generation via Atlas Cloud) but contains inconsistencies — the bundled script also supports Google AI Studio and will read an undeclared GEMINI_API_KEY and contact additional endpoints, and the single required API key grants broad model access and billing risk.

Purpose & Capability

The skill's name and description claim Atlas Cloud image generation for adult content and the declared requirement (ATLASCLOUD_API_KEY) matches that purpose. However, the included script also implements an alternate provider (Google AI Studio) and references GEMINI_API_KEY; that provider capability is not declared in the registry/metadata or the top-level description, which is a mismatch (extra capability present).

Instruction Scope

SKILL.md states prompts and images are sent to api.atlascloud.ai, and requires age confirmation before use — good. The bundled runtime script, however, will also send data to Google (generativelanguage.googleapis.com) if a GEMINI_API_KEY is present or the user selects the google provider. The manifest and requires.env do not declare GEMINI_API_KEY. The script can upload local files and will transmit prompt and image data to external services; those destinations should be declared explicitly. This is scope creep and a transparency issue.

Install Mechanism

No install spec and zero external packages are required. The skill is instruction-only with one shipped Python script that uses only the standard library; no external downloads or opaque installers are used.

Credentials

The registry declares ATLASCLOUD_API_KEY only (reasonable for Atlas use). The script optionally reads GEMINI_API_KEY (Google) though it is not declared — an undeclared credential requirement. The SKILL.md explicitly warns that Atlas keys are not scoped and grant access to all models, which is accurate and indicates a real billing/privilege risk: a single key controls all model usage on the account and billing is pay-as-you-go.

Persistence & Privilege

The skill does not request permanent/global presence (always:false) and does not modify other skills or system-level configuration. It only reads environment variables and writes output image files to disk per normal usage.

What to consider before installing

This skill appears to do what it says (generate adult images) but review and consider the following before installing: - The bundled script will contact Atlas Cloud (declared) and can also contact Google AI Studio if a GEMINI_API_KEY is present or the google provider is chosen — that second credential is not declared in the registry. If you don't want Google involved, do not set GEMINI_API_KEY and avoid using the google provider flag. - ATLASCLOUD_API_KEY grants broad access to all models on your Atlas account and billing is pay-as-you-go. Create a dedicated key for this skill, limit account balance, and monitor usage closely to avoid unwanted charges. - The script can upload local image files; do not upload private or sensitive images you would not want transmitted to third-party services. - If you require higher assurance, inspect the full generate_image.py file locally (it is included) and confirm the network endpoints and code paths. Consider running the script in a controlled environment or sandbox before use. Revoke the dedicated API key when finished. - The skill correctly enforces an 18+ confirmation in SKILL.md, but ensure your agent actually prompts and enforces that step before calling the script.

NSFW Image Generation — Adult Creative AI Image Models

Generate AI images for mature creative projects using models with relaxed content policies. Intended for legitimate adult (18+) artistic and professional use cases such as figure drawing, fashion photography, fine art, and mature illustration.

Recommended model: Wan 2.6 Text-to-Image — cheapest at $0.021/image with 27 preset sizes, prompt expansion, and no content filters.

Age restriction (18+): This skill is strictly for users aged 18 and above. The agent MUST confirm the user's age before first use by asking: "This skill generates mature content. Please confirm you are 18 years or older to proceed." If the user does not confirm, the agent MUST refuse to execute. Minors are strictly prohibited from using this skill.

Data usage note: This skill sends text prompts and image data to the Atlas Cloud API (api.atlascloud.ai) for image generation. No data is stored locally beyond the downloaded output files.

Security note: API keys are read from environment variables and passed via HTTP headers. All prompts are sent through JSON request bodies.

---

Required Environment Variables

Variable	Required	Description
ATLASCLOUD_API_KEY	Yes	Atlas Cloud API key for accessing image generation models

Setup

1. Sign up at https://www.atlascloud.ai
2. Console → API Keys → Create new key
3. Set env: export ATLASCLOUD_API_KEY="your-key"

The API key is tied to your Atlas Cloud account and its pay-as-you-go balance. All usage is billed to this account.

Credential Safety

• Use a dedicated key: Create a separate API key for this skill rather than reusing keys from other applications. Revoke it when no longer needed.
• Do not hardcode keys: Always use environment variables (export ATLASCLOUD_API_KEY="...") — never embed keys in scripts, code, or prompts.
• Monitor usage: Check Console → Usage regularly to track spending and detect anomalies.
• Control your balance: Atlas Cloud uses pay-as-you-go billing — only recharge the amount you plan to use to limit potential exposure.
• Atlas Cloud does not currently support scoped/limited keys — each key grants access to all models on your account. Use balance control as the primary safeguard.

---

Script Usage

This skill includes a Python script for image generation. Zero external dependencies required.

List available image models

python scripts/generate_image.py list-models

Generate an image

python scripts/generate_image.py generate \
  --model "MODEL_ID" \
  --prompt "Your prompt here" \
  --output ./output

Upload a local image (for editing)

python scripts/generate_image.py upload ./local-image.jpg

Edit an image

python scripts/generate_image.py generate \
  --model "MODEL_ID" \
  --prompt "Edit instruction" \
  --image "https://...uploaded-url..."

Run python scripts/generate_image.py generate --help for all options. Extra model params can be passed as key=value (e.g. aspect_ratio=16:9 resolution=2k).

---

Available Models

Wan 2.6 (Alibaba) — Recommended

Model ID	Type	Price	Notes
alibaba/wan-2.6/text-to-image	Text-to-Image	$0.021/image	27 preset sizes up to 2184×936, prompt expansion
alibaba/wan-2.6/image-edit	Image Editing	$0.021/image	Up to 4 reference images, 24 preset sizes

Seedream (ByteDance)

Model ID	Type	Price	Notes
bytedance/seedream-v5.0-lite	Text-to-Image	$0.032/image	Latest, PNG output, prompt optimization
bytedance/seedream-v5.0-lite/edit	Image Editing	$0.032/image	Preserves facial features, lighting, color tones
bytedance/seedream-v4.5	Text-to-Image	$0.036/image	Typography, poster design
bytedance/seedream-v4.5/edit	Image Editing	$0.036/image
bytedance/seedream-v4	Text-to-Image	$0.024/image	Budget option
bytedance/seedream-v4/edit	Image Editing	$0.024/image

Wan 2.5 (Alibaba) — Legacy

Model ID	Type	Price
alibaba/wan-2.5/text-to-image	Text-to-Image	$0.021/image
alibaba/wan-2.5/image-edit	Image Editing	$0.021/image

---

Quick Model Selection

Priority	Model	Price	Best For
1	Wan 2.6 T2I	$0.021	General NSFW, cheapest, most flexible sizes
2	Seedream v4	$0.024	Budget alternative
3	Seedream v5.0 Lite	$0.032	Best quality, PNG output
4	Seedream v4.5	$0.036	Typography, poster design

---

Parameters

Wan 2.6 — Text-to-Image

Parameter	Type	Required	Default	Description
prompt	string	Yes	-	Image description
negative_prompt	string	No	-	What to exclude
size	string	No	1024*1024	Output size (27 presets, see below)
enable_prompt_expansion	boolean	No	false	Auto-expand prompt for better results
enable_sync_mode	boolean	No	false	Wait for result synchronously
enable_base64_output	boolean	No	false	Return Base64 instead of URL
seed	integer	No	random	For reproducible results

Wan 2.6 — Image Edit

Same as text-to-image, plus:

Parameter	Type	Required	Description
images	array	Yes	Images to edit (max 4, 384-5000px per side)

Seedream v5.0 Lite — Text-to-Image

Parameter	Type	Required	Default	Description
prompt	string	Yes	-	Image description
negative_prompt	string	No	-	What to exclude
aspect_ratio	string	No	1:1	1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21, etc.
image_size	string	No	1024	512, 1024, 2048, 4096
prompt_optimization	string	No	-	Standard, Fast
output_format	string	No	png	png, jpeg, webp
seed	integer	No	random	For reproducible results

Seedream v5.0 Lite — Edit

Same as text-to-image, plus:

Parameter	Type	Required	Description
image	string	Yes	Source image URL

Wan 2.6 Image Size Presets (27 options)

1024*1024, 1280*720, 720*1280, 1280*960, 960*1280, 1536*1024, 1024*1536, 1280*1280, 1536*1536, 2048*1024, 1024*2048, 1536*1280, 1280*1536, 1680*720, 720*1680, 2016*864, 864*2016, 1536*864, 864*1536, 2184*936, 936*2184, 1400*1050, 1050*1400, 1680*1050, 1050*1680, 1176*1176, 1560*1560

---

Workflow: Submit → Poll → Download

Text-to-Image Example (Wan 2.6)

# Step 1: Submit
curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/text-to-image",
    "prompt": "A beautiful woman in a flowing red dress standing on a cliff overlooking the ocean at sunset, dramatic lighting, photorealistic",
    "size": "1280*720",
    "enable_prompt_expansion": true
  }'
# Returns: { "code": 200, "data": { "id": "prediction-id" } }

# Step 2: Poll (every 3-5 seconds)
curl -s "https://api.atlascloud.ai/api/v1/model/prediction/{prediction-id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"
# Returns: { "code": 200, "data": { "status": "completed", "outputs": ["https://...url..."] } }

# Step 3: Download
curl -o output.png "IMAGE_URL_FROM_OUTPUTS"

Image Editing Example (Wan 2.6)

curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alibaba/wan-2.6/image-edit",
    "prompt": "Change the outfit to a black evening gown, keep the face and pose unchanged",
    "images": ["https://example.com/photo.jpg"],
    "size": "1280*720"
  }'

Seedream Example

curl -s -X POST "https://api.atlascloud.ai/api/v1/model/generateImage" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "bytedance/seedream-v5.0-lite",
    "prompt": "A stunning portrait of a woman with flowing silver hair in a fantasy forest, ethereal lighting, highly detailed",
    "aspect_ratio": "3:4",
    "image_size": "2048"
  }'

Polling Logic

• processing / starting / running → wait 3-5s, retry (~5-15s for images)
• completed / succeeded → done, get URL from data.outputs[]
• failed → error, read data.error

Atlas Cloud MCP Tools (if available)

atlas_generate_image(model="alibaba/wan-2.6/text-to-image", params={...})
atlas_quick_generate(model_keyword="wan 2.6", type="Image", prompt="...")
atlas_get_prediction(prediction_id="...")

---

Implementation Guide

1. Choose model: Default to Wan 2.6 T2I ($0.021, most flexible). Use Seedream for higher quality or special features (PNG output, typography).

2. Extract parameters: Prompt, size/aspect ratio, negative prompt. Enable prompt expansion for better results.

3. For editing: Use Wan 2.6 Image Edit or Seedream Edit — provide source image URL + edit instructions.

4. Execute: POST to generateImage API → poll result → download.

5. Present result: show file path, offer to open.

Prompt Tips

• Detailed descriptions: These models respond well to detailed, specific prompts
• Negative prompts: Use negative_prompt to exclude undesired elements — "blurry, low quality, distorted, watermark, text"
• Prompt expansion: Enable enable_prompt_expansion (Wan) or prompt_optimization (Seedream) for auto-enhanced prompts
• Style keywords: "photorealistic", "anime", "oil painting", "digital art", "cinematic lighting"
• Composition: Describe poses, camera angles, lighting, and background explicitly