SDXL's mask-based inpainting variant — selectively edit regions of an image while preserving the rest. Full LoRA support with adjustable strength and guidance.
Explore all variants in the SDXL family available on Runflow.
Standard 3.5B text-to-image generation
Image-guided generation with strength control
Mask-based region editing
1–4 step generation, sub-second latency
10+ ControlNet types in one model
Enhanced quality with automated prompt optimization
Every model on Runflow is scored per vertical — not generic leaderboard numbers. Scores come from domain-expert evaluation on real production prompts.
| Use Case | Assessment | Notes |
|---|---|---|
| Portrait | Pending | Portrait inpainting quality |
| Fashion | Pending | Fashion inpainting quality |
| Product | Pending | Product inpainting quality |
| Creative | Pending | Creative inpainting quality |
Full parameter reference for the sdxl-inpainting model endpoint.
| Parameter | Type | Description |
|---|---|---|
| prompt | string | Text description of what to generate in the masked region. |
| image_url | string | URL of the base image to inpaint. Accepts JPEG, PNG, WebP, GIF, AVIF. |
| mask_url | string | URL of the mask image. White regions are edited, black regions are preserved. |
| strength | float | Modification intensity in masked region. 0.01 = subtle; 1.0 = full generation. Default: 0.95. |
| negative_prompt | string | Describe what to exclude from the inpainted region. |
| image_size | object | string | Output dimensions. Presets: square_hd, square, landscape_4_3, landscape_16_9, portrait_4_3, portrait_16_9. |
| num_images | integer | Number of inpainted variations. Range: 1–8. Default: 1. |
| num_inference_steps | integer | Denoising steps. 20–25 for standard, 30–50 for max fidelity. Default: 25. |
| guidance_scale | number | Classifier Free Guidance. 7–9 recommended. Default: 7.5. |
| seed | integer | Reproducibility seed. Same seed + same parameters = identical output. |
| loras | array[object] | Array of LoRA weights to apply during inpainting. |
| embeddings | array[object] | Textual inversion embeddings to apply during generation. |
| expand_prompt | boolean | Auto-expand prompt with additional detail via LLM. Default: false. |
| format | string | Output image format. Options: "jpeg", "png". Default: "jpeg". |
| enable_safety_checker | boolean | Enable content safety filter. Default: true. |
| sync_mode | boolean | If true, returns the image as a data URI. |
Flux AI models are available on many platforms. Here's what makes the Runflow image generation API different.
Binary mask defines exactly which pixels to regenerate — edit specific objects, backgrounds, or details while keeping everything else untouched.
The inpainting model matches lighting, perspective, and style of surrounding unmasked areas for natural-looking edits with no visible seams.
Apply any of 50,000+ community LoRAs during inpainting for style-consistent region replacement — match any visual aesthetic.
SDXL's highly responsive negative prompt system lets you precisely control what to avoid in the inpainted region.
Generate up to 8 inpainted variations per request with different seeds — quickly explore options for the edited region.
Same API, different strengths. Switch models with one parameter change.
Black Forest Labs
FLUX.1 [dev] is a 12B-parameter text-to-image model by Black Forest Labs. Open-w…
ByteDance
Seedream 4.5 by ByteDance — unified generation and editing in one model. Strong…
ByteDance
Seedream 4 by ByteDance — unified generation and editing model with photorealism…
Nano Banana 2 by Google — fast image generation across 4 resolution tiers (0.5K–…
OpenAI
GPT-Image 1.5 by OpenAI — high-fidelity images with strong prompt adherence. Thr…
Nano Banana Pro by Google — premium image generation with sharp detail and natur…
Get API access in minutes. No GPU setup, no infrastructure to manage. Pair with Sentinel to control the quality of every AI-generated image you ship.