[2026.06.11] Release SenseNova-U1-8B-MoT-Interleaved 📖, specially optimized for interleaved image-text generation, with notably improved narrative coherence, character and style consistency, and text-image alignment in multi-page content such as picture books, story books, multi-page PPTs, and illustrated tutorials.
[2026.05.08] Add GGUF quantized checkpoints and layer-offload VRAM modes for low-VRAM single-GPU inference. See Memory-efficient inference. GGUF weights for SenseNova-U1-8B-MoT-Merger are available at 🤗 smthem/SenseNova-U1-8B-MoT-Merger-gguf — many thanks to @smthem for contributing the quantized weights.
[2026.04.30] Release the preview version of the 8-step inference model SenseNova-U1-8B-MoT-8step-preview. In most cases, the image generation quality of this model closely matches that of the base model (see comparison and existing issues). To test this model, you can use the inference scripts, but with the following parameters: --cfg_scale 1.0 --num_steps 8 .
[2026.04.27] Initial release of the inference code for SenseNova-U1.
🌟 Overview
🚀 SenseNova U1 is a new series of native multimodal models that unifies multimodal understanding, reasoning, and generation within a monolithic architecture.
It marks a fundamental paradigm shift in multimodal AI: from modality integration to true unification. Rather than relying on adapters to translate between modalities, SenseNova U1 models think-and-act across language and vision natively.
Unifying visual understanding and generation in an end-to-end architecture from pixel to word opens tremendous possibilities, enabling highly efficient and strong understanding, generation, and interleaved reasoning in a natively multimodal manner.
radar plot
🎨 Interleaved Showcases
Side-by-side comparison between the base SenseNova-U1-8B-MoT and SenseNova-U1-8B-MoT-Interleaved on interleaved image-text generation. With interleaved-specific optimization, the new model delivers stronger narrative coherence, character and style consistency, and text-image alignment across multi-page outputs.
📖 Illustrated Tutorial
SenseNova-U1-8B-MoT
SenseNova-U1-8B-MoT-Interleaved
📚 Story Book
SenseNova-U1-8B-MoT
SenseNova-U1-8B-MoT-Interleaved
🎨 Drawing
SenseNova-U1-8B-MoT
SenseNova-U1-8B-MoT-Interleaved
📑 Presentation / PPT
Single-page PPT — base vs Interleaved:
SenseNova-U1-8B-MoT
SenseNova-U1-8B-MoT-Interleaved
Multi-page PPT — a new capability unique to SenseNova-U1-8B-MoT-Interleaved (not supported by the base model):
🛠️ Quick Start
🌐 Use with SenseNova-Studio
The fastest way to experience SenseNova-U1 is through SenseNova-Studio — a 🆓 free online playground where you can try the model directly in your browser, no installation or GPU required.
Note: To serve more users, U1-Fast has undergone step and CFG distillation, and is dedicated to infographic generation.
🦞 Use with SenseNova-Skills (OpenClaw)
The easiest way to integrate SenseNova-U1 into your own agent or application is through our companion repository SenseNova-Skills (OpenClaw) 🦞, which ships SenseNova-U1 as a ready-to-use skill with a unified tool-calling interface.
✨ Some interesting cases produced through our Skills and Studio
Skill Cases
🤗 Run with transformers (Default)
Setup: Follow the Installation Guide to clone the repo and install dependencies with uv.
♻️ Interleaved Generation
python examples/interleave/inference.py --model_path sensenova/SenseNova-U1-8B-MoT-Interleaved --prompt "I want to learn how to cook tomato and egg stir-fry. Please give me a beginner-friendly illustrated tutorial." --resolution "16:9" --output_dir outputs/interleave/ --stem demo --profile
See examples/README.md for batched inference, JSONL format, prompt enhancement, resolution buckets, and full flag reference.
For production serving, we co-design a dedicated inference stack on top of LightLLM (understanding) and LightX2V (generation). The two engines are disaggregated so that each path can use its own parallelism and resource budget, with a low-overhead transfer channel in between.
On a single node with TP2 + CFG2, this stack delivers roughly ~0.15 s/step and ~9 s end-to-end for a 2048×2048 image on H100 / H200, with a ~2.4–3.2× prefill speedup from our FA3-based hybrid-mask attention over the Triton baseline. Full per-GPU performance are reported in docs/inference_infra.md.
An official docker image is provided for one-command deployment:
docker pull lightx2v/lightllm_lightx2v:20260407
⚙️ Deployment guide (Docker, launch flags, modes, quantization, API test): see docs/deployment.md.
