Codex Launches Dedicated Image Agent UI with Batch Editing
op7418 · x · 2026-07-31
OpenAI's Codex appears to have quietly launched a new UI mode designed specifically for Image Agents.
Key features include:
- Standalone Preview: Clicking a generated image opens a sidebar preview window, allowing direct commenting, erasing, and resizing.
- Immersive Viewing: A toggle in the top-left hides text in the chat, displaying only the generated images for focused review.
- Batch Processing: Users can multi-select images, add them to the input box, and prompt GPT for batch modifications.
The author speculates this is built for the upcoming GPT Image 2.0, and notes that this highly integrated experience could cannibalize a significant portion of existing design agents.
Related event: OpenAI Introduces New Image Editing Workflow for ChatGPT and Codex(3 posts)→
More from Multimodal
- Hailuo AI Demonstrates 15-Second Video Generation from a Single Image — LudovicCreator · 2026-07-31
- MiniMax H3 Video Model Enters Chatbot Arena, Open Weights Coming Soon — arena · 2026-07-31
- Mind-Blowing AI Concept: Visualizing Pigeon 'Flight-Mile' Delivery to Dodge Traffic — sivakumaranvlsi · 2026-07-31
- MiniMax H3 Video Model Now Available on Vercel AI Gateway — evilrabbit_ · 2026-07-31
- Testing Flux 3: Generating Synchronized Split-Screen Videos via Complex Prompts — umesh_ai · 2026-07-31
- MPIE-Bench: Evaluating Anatomical Errors in Multi-Person Image Editing — muset-ai · 2026-07-31