Search

ByteDance Unveils Bagel Open Source Multimodal AI Model With Support for Generating, Editing Images

ByteDance’s Bagel is a visual language model (VLM) with 14 billion parameters.

Advertisement
Highlights
  • Bagel is said to outperform Gemini-2-exp in image editing
  • It is said to outperform Qwen2.5-VL in image understanding
  • The AI model is available to download with an Apache 2.0 licence
ByteDance Unveils Bagel Open Source Multimodal AI Model With Support for Generating, Editing Images

ByteDance said Bagel can generate and edit images while using reasoning capabilities

Photo Credit: Unsplash/Markus Winkler

ByteDance released a new multimodal artificial intelligence (AI) model last week. Dubbed Bagel, it is a visual language model (VLM), which is capable of understanding, generating, and editing images. The Beijing-based tech giant has open-sourced the AI model, and it is available to download via popular AI repositories such as GitHub and Hugging Face. The company claims Bagel is capable of free-form visual manipulation, multiview synthesis, and world navigation, which makes it more capable in image editing compared to existing open-source VLMs.

ByteDance's Bagel Outperforms Gemini-2-exp in Image Editing

A GitHub listing page sheds more light on ByteDance's Bagel AI model, including its weights and datasets. However, the company did not provide details about the post-training processes, or the architecture of the model. It is currently available with a permissive Apache 2.0 licence, which allows both academic and commercial usage.

Bagel is a multimodal AI model that accepts both text and images as input. The open-source VLM features a total of 14 billion parameters, out of which seven billion remain active at a time. ByteDance claims that the model was trained on large-scale interleaved multimodal data. This means that different types of data, such as text and images, were combined while feeding the AI system. As a result, the model learned from both modalities jointly, instead of separately.

This method allows foundation models to gain context between different modalities. For instance, if Bagel was fed images and their captions together, it would be better able to understand what the text exactly represents in the visual medium. This would result in more efficient output, as per the company.

ByteDance also claims that the AI model displays better image editing capabilities compared to existing open-source VLMs. It can perform complex tasks such as adding emotion to an image, removing, replacing or adding elements, style transfer, as well as making free-form edits. The company claims that with this ability, Bagel is capable of providing significantly higher output while world-modelling.

World-modelling refers to an AI system's internal understanding of how the real world functions visually. This would include the relationship between different objects, physical context, and the effect of physical factors such as light, wind, rain, and gravity.

Based on internal testing, ByteDance claims that Bagel was able to outperform Qwen2.5-VL-7B, a similarly sized model, in image understanding. It is also said to score higher in image generation benchmarks than Janus-Pro-7B and Flux-1-dev. Additionally, it is also said to beat Gemini-2-exp on the GEdit-Bench for image editing.

Those who wish to try out the AI model without locally running it can head to Hugging Face, where ByteDance has set up a cloud-based interface to test its image analysis, generation, and editing.

For the latest tech news and reviews, follow Gadgets 360 on X, Facebook, WhatsApp, Threads and Google News. For the latest videos on gadgets and tech, subscribe to our YouTube channel. If you want to know everything about top influencers, follow our in-house Who'sThat360 on Instagram and YouTube.

 
Show Full Article
Please wait...
Advertisement

Related Stories

Popular Mobile Brands
  1. Lenovo Yoga Tab Plus With 12.7-Inch Screen, AI Features Launched in India
  2. Nothing Announces India-Exclusive Drop Event for Its Flagship Phone 3
  3. Elon Musk's xAI Releases Grok 4 AI Model and a $300 Monthly Subscription Plan
  4. Pixel Drop Arrives With Free Google AI Pro Plan for Pixel 9 Pro Owners
  5. JBL Tour Pro 3 TWS With Smart Charging Case Launched in India
  6. iPhone 17 Air Could Be Available in Four Colour Options
  7. Samsung Galaxy Z Fold 7 With 8-Inch Inner Display Launched in India
  1. Grok 4 AI Model Launched by Elon Musk's xAI Alongside the World’s Most Expensive AI Subscription Plan
  2. Nothing Phone 3 India Exclusive Drop Event Set to Take Place on July 12; First 100 Buyers Get Free Headphone 1
  3. JBL Tour Pro 3 TWS With Touch Display, Up to 44-Hour Playback Time Launched in India
  4. Apple Reportedly Working on Sealed-Device Update System for MacBook Units at Apple Stores
  5. Apple Adds iCloud Passwords Support For Mozilla Firefox Via Browser Extension on Windows
  6. OpenAI Reportedly Working On an AI-Powered Web Browser, to Compete With Google Chrome
  7. Lenovo Yoga Tab Plus Launched in India With Snapdragon 8 Gen 3 SoC, 10,200mAh Battery
  8. Apple Support App Reportedly Getting a ChatGPT-Style AI Chatbot to Assist Users
  9. Apple Vision Pro Successor to Reportedly Launch in 2025 With M4 Chip, Better Components for AI
  10. Gemini Rolls Out to Wear OS Smartwatches With Support for Natural Language Commands
© Copyright Red Pixels Ventures Limited 2025. All rights reserved.
Trending Products »
Latest Tech News »