WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation
Paper • 2511.11434 • Published • 47
Bagel-weave
📌 This is the official Bagel implementation of Weave: A Benchmark for Evaluating Multimodal Editing Models
Bagel-weave is finetuned by WEAVE-100k.
License
BAGEL-weave is licensed under the Apache 2.0 license. It is finetuned from Bagel-7B-MOT, Qwen2.5-7B-Instruct and siglip-so400m-14-384-flash-attn2 model, and uses the FLUX.1-schnell VAE model, all under Apache 2.0.
✍️ Citation
- Downloads last month
- 9
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support