generate_image
Create images from text descriptions using AI-powered image generation. Transform written prompts into visual content through the DeepInfra API.
Instructions
Generate an image from a text prompt using DeepInfra OpenAI-compatible API.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Implementation Reference
- src/mcp_deepinfra/server.py:47-62 (handler)The generate_image tool handler, registered with @app.tool(), generates an image URL from a text prompt using DeepInfra's OpenAI-compatible images.generate API.
@app.tool() async def generate_image(prompt: str) -> str: """Generate an image from a text prompt using DeepInfra OpenAI-compatible API.""" model = DEFAULT_MODELS["generate_image"] try: response = await client.images.generate( model=model, prompt=prompt, n=1, ) if response.data: return f"Generated image URL: {response.data[0].url}" else: return "No image generated" except Exception as e: return f"Error generating image: {type(e).__name__}: {str(e)}" - src/mcp_deepinfra/server.py:31-42 (helper)Global DEFAULT_MODELS dictionary providing the default model ('Bria/Bria-3.2') for the generate_image tool.
DEFAULT_MODELS = { "generate_image": os.getenv("MODEL_GENERATE_IMAGE", "Bria/Bria-3.2"), "text_generation": os.getenv("MODEL_TEXT_GENERATION", "meta-llama/Llama-2-7b-chat-hf"), "embeddings": os.getenv("MODEL_EMBEDDINGS", "sentence-transformers/all-MiniLM-L6-v2"), "speech_recognition": os.getenv("MODEL_SPEECH_RECOGNITION", "openai/whisper-large-v3"), "zero_shot_image_classification": os.getenv("MODEL_ZERO_SHOT_IMAGE_CLASSIFICATION", "openai/gpt-4o-mini"), "object_detection": os.getenv("MODEL_OBJECT_DETECTION", "openai/gpt-4o-mini"), "image_classification": os.getenv("MODEL_IMAGE_CLASSIFICATION", "openai/gpt-4o-mini"), "text_classification": os.getenv("MODEL_TEXT_CLASSIFICATION", "microsoft/DialoGPT-medium"), "token_classification": os.getenv("MODEL_TOKEN_CLASSIFICATION", "microsoft/DialoGPT-medium"), "fill_mask": os.getenv("MODEL_FILL_MASK", "microsoft/DialoGPT-medium"), }