How to Generate an Image
Step-by-step guide to generating images with WaveSpeedAI.
Quick Start
Web Interface
- Go to wavespeed.ai/models
- Select a text-to-image model (e.g., FLUX, Seedream, Nano Banana)
- Enter your prompt
- Click Run
API
curl --location --request POST 'https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev' \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"prompt": "A majestic mountain landscape at sunset, cinematic lighting",
"size": "1024*1024",
"num_inference_steps": 28,
"guidance_scale": 3.5,
"num_images": 1,
"seed": -1
}'Recommended Models
| Model | Best For | Speed |
|---|---|---|
| FLUX Dev | General purpose, high quality | Fast |
| FLUX Schnell | Quick iterations | Very fast |
| Seedream | Versatile, good prompt following | Medium |
| Nano Banana Pro | High quality, realistic | Fast |
Common Parameters
| Parameter | Description | Example |
|---|---|---|
prompt | What to generate | ”A cat in space” |
width | Output width | 1024 |
height | Output height | 768 |
num_inference_steps | Quality (more = better) | 20-50 |
seed | For reproducibility | 12345 |
Example: High Quality Image
{
"prompt": "A fluffy orange cat sitting on a windowsill, soft afternoon sunlight streaming through the window, bokeh background, photography style, 4K, high detail",
"width": 1024,
"height": 1024,
"num_inference_steps": 30
}Example: Multiple Variations
Generate multiple images with different seeds by making separate API calls:
# First variation (seed: 1)
curl --location --request POST 'https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev' \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"prompt": "A cat in space",
"size": "1024*1024",
"num_inference_steps": 28,
"guidance_scale": 3.5,
"seed": 1
}'
# Second variation (seed: 2)
curl --location --request POST 'https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-dev' \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"prompt": "A cat in space",
"size": "1024*1024",
"num_inference_steps": 28,
"guidance_scale": 3.5,
"seed": 2
}'Tips for Better Results
- Be specific — Include details about subject, style, lighting
- Use Prompt Enhancer — Click the button to optimize your prompt
- Start small — Test with lower resolution first
- Check model README — Each model has specific tips
See How to Write Better Prompts for more tips.