Unverified50% confidenceFactExact time
The Abyssal Garden project uses no images, 3D models, audio files, or third-party libraries, and all content is generated in real time by code at load time.
1
Sources
50%
Confidence
Long-term
Relevance
11/14/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe original post did not include technical details, a demo video, or a code repository link.63% similarUnverifiedThe developer explicitly stated that no AI image generators were used in the game; the 3D world, characters and store art are all procedurally generated by the game's own code based on real elevation and river data; bird songs and river sounds are field recordings.61% similarUnverifiedThe Opus series has not been trained on video or audio data; the model renders visual content purely through code.61% similarUnverifiedModly is released as a desktop application; users only need to install the app and import an image to start 3D model generation, without needing to set up a deep learning environment.61% similarUnverifiedThe DeepSeek vision version does not call external tools when processing images; instead, the model itself directly perceives image content, with an integrated image encoding module.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1170759API
curl https://kongchang.com/api/v1/knowledge/claims/1170759MCP
get_claim(id=1170759)