Inference Logoinference.sh

Image Generation

Generate images with AI models.


Using the Grid

The fastest way to generate images:

  1. Go to Apps
  2. Find stable-diffusion or flux
  3. Enter a prompt
  4. Click Run

Example Prompts

StylePrompt
Photorealistic"Professional headshot of a woman, studio lighting, 4k"
Illustration"Cute cartoon fox in a forest, children's book style"
Abstract"Flowing waves of blue and purple, digital art"
Product"White sneakers on marble surface, product photography"

With Python SDK

python
1from inferencesh import inference2 3client = inference(api_key="inf_your_key")4 5result = client.run({6    "app": "infsh/stable-diffusion",7    "input": {8        "prompt": "A serene Japanese garden with cherry blossoms",9        "negative_prompt": "blurry, low quality",10        "num_images": 1,11        "size": "1024x1024"12    }13})14 15image_url = result["output"]["images"][0]["uri"]16print(f"Generated: {image_url}")

With JavaScript SDK

typescript
1import { inference } from '@inferencesh/sdk';2 3const client = inference({ apiKey: 'inf_your_key' });4 5const result = await client.run({6  app: 'infsh/stable-diffusion',7  input: {8    prompt: 'A serene Japanese garden with cherry blossoms',9    negative_prompt: 'blurry, low quality',10    num_images: 1,11    size: '1024x1024'12  }13});14 15console.log('Generated:', result.output.images[0].uri);

With Agent

Create an agent with stable-diffusion as a tool:

code
1You: Generate a logo for a coffee shop called "Morning Brew"2 3Agent: I'll create a logo for Morning Brew.4       [Calling stable-diffusion...]5       6       Here's your logo! I generated a warm, inviting design7       with a coffee cup and sunrise motif.8       9       Would you like variations or a different style?

AppBest For
stable-diffusionGeneral purpose, flexible
fluxHigh quality, detailed
dalleCreative, artistic
sdxl-turboFast generation
controlnetGuided generation (pose, edge)

Model Configuration

Use setup parameters to load specific checkpoints or change precision:

python
1client.run({2    "app": "infsh/stable-diffusion",3    "setup": {4        "model_id": "stabilityai/stable-diffusion-xl-base-1.0",5        "precision": "fp16"6    },7    "input": { ... }8})

Tips

Be specific:

code
1 "a dog"2 "Golden retriever puppy playing in autumn leaves, warm sunlight, shallow depth of field"

Use negative prompts:

code
1negative_prompt: "blurry, low quality, distorted, ugly, duplicate"

Try different models:

  • SDXL for quality
  • Turbo for speed
  • Flux for details

Next

Audio Transcription

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.