A bit weird, but okay. (Don't get me wrong it's SOTA for editing, but definitely not generation) Thoughts?
Summary
The comment acknowledges that the model is state-of-the-art for editing but not for generation.
Similar Articles
Is No One Noticing That GPT Images 2.0 “Editing” Is Full-Frame Regeneration?
This article analyzes ChatGPT's image editing feature, arguing that it performs full-frame regeneration via DALL-E rather than localized editing, based on network traffic and metadata evidence.
Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning
Uni-Edit proposes using intelligent image editing as a single general task to simultaneously improve unified multimodal models' understanding, generation, and editing capabilities, with an automated data synthesis pipeline creating complex editing instructions.
Bootstrap Your Generator: Unpaired Visual Editing with Flow Matching
Bootstrap Your Generator (ByG) is a framework for unpaired training of flow matching editing models, leveraging base model knowledge and gradient routing to achieve state-of-the-art results in data-scarce image and video editing tasks.
Jokes aside this just looks and sounds way too well done
A new AI model generates impressively realistic video and audio, with many observers noting the high quality of the output.
@antoine_chaffin: Reason-ModernColBERT nearly solved BrowseComp-Plus, smashing SOTA and outperforming models models 54× bigger Not bad fo…
Reason-ModernColBERT achieves near-perfect results on BrowseComp-Plus, surpassing SOTA and models 54× larger, then Agent-ModernColBERT further improves with minimal training.