SenseNova U1 V2 offers a cheaper route for infographic agents
SenseTime has released V2 of the SenseNova U1 generation model. The update is meant to make dense small text clearer and complex crowded layouts more stable than V1.
A bug that could produce an all-black has also been fixed. The core model specs are unchanged: it uses an 8B MoT design, runs on one RTX 3090 or 4090, and takes about 8 to 12 seconds to create a 1024×1024 image.
It is released under , which gives broad room for reuse. SenseTime also provides a smaller 0.4B 8-step LoRA for faster , plus an Interleaved variant for mixing text and images in one generation flow.
Key points
- SenseNova U1 V2 is an focused on generation.
- The update targets clearer small text and more stable dense layouts.
- The model can run on a single RTX 3090 or 4090 GPU.
- A 1024×1024 image takes about 8 to 12 seconds to generate.
- The 0.4B 8-step LoRA is meant to reduce time.