OATDA Image Generation

Generate images from text descriptions using AI models through OATDA's unified API.

API Key Resolution

All commands need the OATDA API key. Resolve it inline for each exec call:

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}"

If the key is empty or null, tell the user to get one at https://oatda.com and configure it.

Security: Never print the full API key. Only verify existence or show first 8 chars.

Model Mapping

Default: openai / dall-e-3 if no model specified.

> ⚠️ Models update frequently. If a model ID fails, query oatda-list-models with ?type=image for the latest available models.

Discovering Model-Specific Parameters

Different models support different parameters (sizes, quality, styles, masks, watermarks, negative prompts, etc.). Query before generating:

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X GET "https://oatda.com/api/v1/llm/models?type=image" \
  -H "Authorization: Bearer $OATDA_API_KEY" | jq '.image_models[] | {id, supported_params}'

This returns each model's supported_params with type, allowed values, defaults, and descriptions. File-type parameters (like mask) require public URLs.

API Call

CRITICAL: The endpoint is /api/v1/llm/generate-image (NOT /api/v1/llm/image — that's vision analysis).

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X POST "https://oatda.com/api/v1/llm/generate-image" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -d '{
    "provider": "<PROVIDER>",
    "model": "<MODEL>",
    "prompt": "<IMAGE_DESCRIPTION>",
    "size": "1024x1024",
    "quality": "standard",
    "n": 1,
    "numberOfImages": 1
  }'

Common Parameters

• prompt: Image description (1-4000 characters)
• size: "1024x1024", "1792x1024", "1024x1792", "2K", "4K" (model-dependent)
• quality: "standard", "hd", "auto", "low", "medium", "high"
• n and numberOfImages: Number of images (1-10) — set both to same value
• aspectRatio: "1:1", "16:9", "9:16", "3:2", "2:3", "4:3", "3:4"
• style: "vivid" (dramatic) or "natural" (realistic)
• background: "auto", "transparent", "opaque"
• outputFormat: "png", "jpeg", "webp"
• model_params: Model-specific key-value pairs (see discovery above)

model_params Examples

• DALL-E 3: {"style": "vivid", "quality": "hd"}
• GPT-Image-1: {"quality": "high", "background": "transparent", "outputFormat": "png"}
• Imagen 4: {"sampleImageSize": "2K", "personGeneration": "allow_adult"}
• Seedream: {"size": "4K", "watermark": false}
• Wan 2.6: {"seed": "42", "negative_prompt": "blurry", "prompt_extend": true}

Response Format

{
  "success": true,
  "url": "https://cdn.example.com/generated-image.png",
  "all_images": [
    {"url": "https://cdn.example.com/image-1.png"},
    {"url": "https://cdn.example.com/image-2.png"}
  ],
  "revised_prompt": "A detailed cyberpunk cityscape at night..."
}

Show image URL(s) from all_images array (or url field if single). Mention revised_prompt if present.

Error Handling

Examples

DALL-E 3 HD

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X POST "https://oatda.com/api/v1/llm/generate-image" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -d '{
    "provider": "openai",
    "model": "dall-e-3",
    "prompt": "A cyberpunk city at night with neon lights reflecting on wet streets",
    "size": "1024x1024",
    "quality": "hd",
    "n": 1,
    "numberOfImages": 1,
    "model_params": {"style": "vivid"}
  }'

GPT-Image-1 Transparent PNG

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X POST "https://oatda.com/api/v1/llm/generate-image" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -d '{
    "provider": "openai",
    "model": "gpt-image-1",
    "prompt": "A sleek minimalist logo of a mountain, clean vector style",
    "n": 1,
    "model_params": {"quality": "high", "background": "transparent", "outputFormat": "png"}
  }'

Seedream 4K No Watermark

export OATDA_API_KEY="${OATDA_API_KEY:-$(cat ~/.oatda/credentials.json 2>/dev/null | jq -r '.profiles[.defaultProfile].apiKey' 2>/dev/null)}" && \
curl -s -X POST "https://oatda.com/api/v1/llm/generate-image" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OATDA_API_KEY" \
  -d '{
    "provider": "bytedance",
    "model": "seedream-4-5-251128",
    "prompt": "A majestic dragon flying over a fantasy kingdom at sunset",
    "model_params": {"size": "4K", "watermark": false}
  }'

Notes

• Endpoint is /api/v1/llm/generate-image — NOT /api/v1/llm/image (vision analysis)
• Set both n and numberOfImages to the same value for compatibility
• Image URLs may be temporary — recommend downloading promptly
• Max prompt length: 4000 characters
• Use oatda-vision-analysis for analyzing images
• Use oatda-list-models for available image models
• In Telegram/chat: Extract only the image URL from the response (jq -r '.url'), do NOT dump raw JSON. Present as clickable link or describe the image.