Bagel

Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both text and images.

Inference$ Commercial useFrom 1 credit per run

About Bagel

Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both text and images.

image-to-textvlm

Pricing

A run with the default settings costs 1 credits. The exact cost updates in the playground as you change settings, and you're only charged when you press Run. Failed runs are refunded automatically.

Inputs

image_urlfilerequired

The image for the query.

prompttextarearequired

The prompt to query the image with.

seedinteger

The seed to use for the generation.

enable_safety_checkerbooleandefault: true

Authorized callers may set false to request relaxed screening.

More from Bagel

Bagel

Bagel is a 7B parameter from Bytedance-Seed multimodal model that can generate both text and images.

multimodal

text-to-image

Bagel

Bagel is a 7B parameter multimodal model from Bytedance-Seed that can generate both images and text.

image-editing

image-to-image

Related image to json models

VGGT-1B

Turn images or video into a detailed 3D scene with depth, camera poses, and a colored point cloud.

image-to-json

Bria Ad Delayer: Convert Flat Ads into Editable Layers | fal

Turn any flat ad image into fully editable layers —background, product and logo cutouts, live text with typography, and vector shapes. Commercial-safe, structured JSON output

utilityediting

image-to-json