Unverified50% confidenceBenchmarkExact time
The Along the River During the Qingming Festival scene generated by Luna Max over an hour and a half proactively rendered characters, roof textures, and shop fronts as textures displayed in the 3D scene, making full use of GPT-image's image generation capabilities.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/26/2026
First Seen
Valid until: 12/25/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-6 can replicate an image into an interactive 3D web scene, completing the restoration of details such as water surfaces, leaves, and furniture through two iterations (24 minutes for the first version and 27 minutes for the second).62% similarUnverifiedThe second step of the workflow uses the tool's image generation feature (referred to in the video as the "small circle" function) to generate three-view images of the protagonist character and background images.62% similarUnverifiedCodex's built-in image_gen skill can call the GPT image model to generate images, and the computer use plugin includes operations such as app control, screen recording, and keyboard input.61% similarUnverifiedSenseTime is reportedly developing a multimodal image large model called U1 Pro, internally benchmarked against GPT Image 2, targeting design scenarios, supporting long-range generative review loops, and capable of outputting at up to 8K resolution.61% similarUnverifiedWorldClaw calls models including GPT Image 2, SAM3D, and Hunyuan3D at different stages to handle image generation, segmentation, and 3D reconstruction.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/951558API
curl https://kongchang.com/api/v1/knowledge/claims/951558MCP
get_claim(id=951558)