bytedance/bagel

🥯ByteDance Seed's Bagel Unified multimodal AI that generates images, edits images, and understands images in one 7B parameter model🥯

Input
Configure the inputs for the AI model.

Random seed for reproducible results

Task to perform

Input image for editing or understanding tasks

Text prompt for generation, editing, or understanding

1
10

Image guidance scale for preserving input image details

Output image format

0
1

Minimum CFG renorm value

1
20

Text guidance scale for how closely to follow the prompt

1
100

Image compression quality for lossy formats

1
10

Distribution of denoising steps between composition and details

CFG renormalization method

Enable chain-of-thought reasoning for better results

1
100

Number of denoising steps

Output
The generated output will appear here.

No output yet

Click "Generate" to create an output.