Flux Fill Dev

Flux Fill Dev

Playground

FLUX.1 Fill [dev] is a 12B-parameter rectified flow transformer for text-guided image inpainting that fills areas of existing images from text prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

FLUX Fill Dev

FLUX Fill Dev is a powerful AI-powered inpainting model that fills in masked regions of images based on text prompts. Upload an image and mask, describe what should appear in the masked area, and the model seamlessly generates new content that blends naturally with the surrounding image.

Why It Stands Out

• Precise inpainting: Generate new content only in masked regions while preserving the rest.
• Prompt-guided generation: Describe exactly what should appear in the masked area.
• Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
• LoRA support: Apply up to 3 custom LoRA models for specific styles.
• Flexible resolution: Width and height adjustable from 256 to 1536 pixels.
• Batch generation: Create multiple variations in a single request.
• Reproducibility: Use the seed parameter to recreate exact results.

Parameters

How to Use

1. Upload your source image — drag and drop a file or paste a public URL.
2. Upload or create a mask image — white areas will be regenerated, black areas preserved.
3. Write a prompt describing what should appear in the masked region. Use the Prompt Enhancer for AI-assisted optimization.
4. Add LoRAs (optional) — apply up to 3 custom style LoRAs.
5. Adjust parameters (optional) — set dimensions, guidance scale, and num_images.
6. Click Run and download your edited image.

Best Use Cases

• Object Replacement — Replace objects in images with new ones.
• Background Editing — Change or extend backgrounds seamlessly.
• Content Addition — Add new elements like clothing, accessories, or objects.
• Photo Repair — Remove unwanted elements and fill with appropriate content.
• Creative Compositing — Blend new elements into existing scenes naturally.

Pricing

Pro Tips for Best Quality

• Create clean, precise masks — white for areas to regenerate, black for areas to keep.
• Be specific in your prompt about what should appear in the masked area.
• Use higher guidance scale (25–35) for stronger prompt adherence.
• Generate multiple images (num_images > 1) to explore variations.
• Use LoRAs to apply consistent styles across multiple inpainting jobs.
• Ensure mask edges are smooth for better blending results.

Notes

• Maximum of 3 LoRAs per generation.
• Width and height must be between 256 and 1536 pixels.
• Ensure uploaded image URLs are publicly accessible.
• Processing time varies based on resolution and current queue load.
• Please ensure your content complies with usage guidelines.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/flux-fill-dev" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1024*1024",
    "num_inference_steps": 28,
    "seed": 0,
    "guidance_scale": 30,
    "num_images": 1,
    "loras": []
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"