Bria/fibo_edit
🥳 For a limited time, Fibo Edit is free on WhollyAPI! 🥳 Create production-grade visuals with FIBO Edit, an open-source image editing model featuring native masking and a lightweight 8B architecture. YOUR AI, YOUR RULES. Start building, editing, and generating images with speed and flexibility—all on WhollyAPI.
Try the model with a sample request using the same API shape shown in the reference page.
Text-based edit instruction (e.g., 'make the sky blue', 'add a cat'). This parameter serves as the text prompt.. (Default: empty)
Please upload an image file
Please upload an image file
If true, returns 422 on images or mask moderation failure. Default: true
Number of diffusion steps. Default: 50, Min: 20, Max: 50 (Default: empty, 20 ≤ steps_num ≤ 50)
If true, returns 422 on visual output moderation failure. Default: true
If true, returns 422 on instruction moderation failure. Default: true
A string containing the structured edit instruction in JSON format. Use this instead of instruction for precise, programmatic control.. (Default: empty)
Determines how closely the generated image should adhere to the instruction. Default: 5, Min: 3, Max: 5 (Default: empty, 3 ≤ guidance_scale ≤ 5)
A text prompt specifying concepts, styles, or objects to exclude from the edited image.. (Default: empty)
Seed for deterministic generation. If omitted, a random seed is generated. (Default: empty)
Adjust settings and run the demo to see the model output generated here in real-time.
