Unverified50% confidenceFactExact time
MOSS-Image uses the DT (Diffusion Transformer) architecture.
1
Sources
50%
Confidence
Long-term
Relevance
10/29/2026
First Seen
Sources
Run 8K Images on 6GB VRAM! Hands-On Test of Fudan's Open-Source MOSS-Image Model
bilibiliAI绘画教学视频10/29/2026
Related Entities
Related Claims
VerifiedThe Wan (万象) video generation model is based on the DiT (Diffusion Transformer) architecture.65% similarUnverifiedMixture-of-Transformers (MoT) keeps an independent Transformer branch for each modality, allowing information interaction through cross-modal attention at specified layers.65% similarUnverifiedMeta's Muse Image adopts a Transformer-based masked generation architecture and has a significant advantage in image generation speed.63% similarUnverifiedHuawei's Pangu-Weather adopts a 3D Swin Transformer architecture.63% similarUnverifiedThe core idea of DiT is to split the image into patches and treat them as a sequence input to the Transformer, and to inject timestep and class conditions through adaptive layer normalization (adaLN).61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1112054API
curl https://kongchang.com/api/v1/knowledge/claims/1112054MCP
get_claim(id=1112054)