sdxl-1.0
Open-source workhorse. Massive ecosystem. ControlNet compatible. The most versatile image model available.
Specifications
| Model ID |
sdxl-1.0
|
| Provider | Stability AI |
| Type | Image Generation |
| Architecture | Latent Diffusion (Dual Text Encoder, CLIP + OpenCLIP) |
| Max Resolution | 1024×1024 |
| Supported Sizes | 512×512, 768×768, 1024×1024, 1024×768, 768×1024 |
| Avg Generation Time | ~2 seconds |
| Cost | From $0.01/image |
| ControlNet | ✓ Supported (Canny, Depth, Pose, Tile, IP-Adapter) |
| Img2Img | ✓ Supported |
| Inpainting | ✓ Supported |
| Negative Prompt | ✓ Supported |
| Seed Control | ✓ Supported (reproducible outputs) |
| Steps Range | 10–50 (default: 30) |
| Guidance Scale | 1.0–20.0 (default: 7.5) |
| Scheduler Options | DPM++ 2M Karras, Euler A, DDIM, UniPC |
| Output Formats | PNG, JPEG, WebP |
| Batch Generation | Up to 4 images per request |
| API Endpoint |
POST /v1/images/generations
|
| OpenAI Compatible | ✓ Yes — use the standard OpenAI SDK |
Generated with sdxl-1.0
API integration
OpenAI-compatible. Drop-in replacement.
from openai import OpenAI
client = OpenAI(
base_url="https://api.fluxpool.ai/v1",
api_key="fp_your_api_key"
)
response = client.images.generate(
model="sdxl-1.0",
prompt="Isometric RPG village with tavern and market stalls, vibrant pixel art",
size="1024x1024"
)
print(response.data[0].url)
"Isometric RPG village with tavern and market stalls, vibrant pixel art"
Related models
Best overall quality. Superior prompt adherence. Photorealistic.
Up to 2048×2048 • ~3s • $0.03/image
Try it →Excellent Asian aesthetics. Strong text rendering. Multilingual prompts.
Up to 2048×2048 • ~4s • $0.02/image
Try it →Best-in-class text rendering in images. Graphic design focus.
Up to 2048×2048 • ~5s • $0.04/image
Try it →Design-oriented. Clean compositions. Great for marketing assets.
Up to 1024×1024 • ~3s • $0.02/image
Try it →