AI Applications

Choose an AI model to get started

Image Generation

FLUX.1 Kontext Dev

Fast endpoint for Flux Kontext, optimized with pruna framework. Specialized for precise image editing and manipulation through text prompts with pro-level editing fidelity.

Cost: 4 credits

Input

Prompt

The text description to generate an image from. This is the core input that drives the output

Input Image (Optional)

Upload an image to edit (optional for image-to-image generation)

The input image for image-to-image generation. Upload an image file and it will be automatically processed

Aspect Ratio

Aspect ratio of the output image. "match_input_image" will use the same ratio as the input image

Inference Steps

How many denoising steps to run during generation. More steps may improve quality, at the cost of speed

Guidance Scale

CFG controls how closely the image follows the prompt. Higher values = stronger prompt adherence, but may reduce creativity

Seed

A seed value for reproducibility. The same seed + prompt + model version = same image. Use -1 to randomize

Enable Safety Checker

If enabled, content will be checked for safety violations

Output Format

The file format of the generated image

Output Quality

Applies to jpeg and webp formats. Defines compression quality (1-100)

Output

Generated content will appear here

Example Results

Prompt:

input image

Prompt:

A scientist raccoon eating ice cream in a datacenter, photorealistic style

Frequently Asked Questions

What is FLUX.1 Kontext Dev and how is it different from other image generators?: FLUX.1 Kontext Dev is a specialized AI model for precise image editing and manipulation, optimized by PrunaAI for 5x faster performance. Unlike general text-to-image models, it excels at making specific, localized changes to images while preserving other elements, offering pro-level editing fidelity.
Can I use this model for both text-to-image and image-to-image generation?: Yes! FLUX.1 Kontext Dev supports both modes. You can generate images from text prompts alone, or upload an existing image and use text prompts to edit and transform specific parts of it. Uploaded images are automatically processed and stored securely.
What types of image editing can I perform with this model?: You can perform various editing tasks including: style transfers (watercolor, oil painting, sketches), object modifications, clothing changes, background transformations, lighting adjustments, and maintaining character consistency across edits.
How do I write effective prompts for image editing?: For best results, be specific about what you want to change while mentioning what should remain unchanged. For example: 'Transform the red car into a blue sports car, maintaining all other elements' or 'Change the background to a sunset scene while keeping the subject unchanged'.
What aspect ratios and output formats are supported?: The model supports various aspect ratios including 1:1, 16:9, 21:9, 3:2, 2:3, 4:5, 5:4, 3:4, 4:3, 9:16, and 9:21. You can also choose 'match_input_image' to automatically match the uploaded image's aspect ratio. Output formats include JPEG, PNG, and WebP.
What do the advanced parameters like guidance scale, inference steps, and safety checker do?: Guidance scale controls how closely the output follows your prompt (higher values = stronger adherence but may reduce creativity). Inference steps determine the number of denoising steps (more steps may improve quality but take longer). The safety checker filters content for safety violations. You can generate 1-4 images per request and control output quality for JPEG/WebP formats.