← All models
Bagel
bagel
Image generationby bytedance
images
Data schema
Input
| Field | Type | Description |
|---|---|---|
| seed | integer | Random seed for reproducible results |
| task | —enum: text-to-image, image-editing, image-understanding | Task to perform |
| image | string | Input image for editing or understanding tasks |
| promptrequired | string | Text prompt for generation, editing, or understanding |
| cfg_img_scale | number | Image guidance scale for preserving input image details |
| output_format | —enum: webp, jpg, png | Output image format |
| cfg_renorm_min | number | Minimum CFG renorm value |
| cfg_text_scale | number | Text guidance scale for how closely to follow the prompt |
| output_quality | integer | Image compression quality for lossy formats |
| timestep_shift | number | Distribution of denoising steps between composition and details |
| cfg_renorm_type | —enum: global, local, text_channel | CFG renormalization method |
| enable_thinking | boolean | Enable chain-of-thought reasoning for better results |
| num_inference_steps | integer | Number of denoising steps |