#3030th of 52 in Open modelsFor image, video and design, image and design
sensenova-u1
Open 8B multimodal model for image generation, editing and visual Q&A
- Stars
- 6.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Language
- Python
2 on 18 Apr 20266,922 on 31 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
SenseNova-U1 and U1.5 are open-weight native multimodal models (8B-MoT, plus an A3B variant) that handle text-to-image, image editing, interleaved image-text generation and visual question answering in one model. The repo ships Python inference scripts for Transformers, optional GGUF checkpoint loading, 8-step LoRA checkpoints, a ComfyUI workflow and full-parameter fine-tuning code. Production serving is documented separately with LightLLM and LightX2V.
Who it is for: Engineers running open multimodal models for image generation and editing
Strengths
- One checkpoint covers text-to-image, editing, interleaved generation and VQA
- Native 4K generation and bounding-box or reference-based visual control in U1.5
- 8-step LoRA and GGUF checkpoints reduce latency and VRAM use
- Training code, technical reports and a ComfyUI workflow are included
Weaknesses
- README admits dense text, hands, small faces and multi-turn edits can still fail
- Official GGUF weights for U1.5 are not out yet; current GGUFs are community-made
- No tagged release; weights are distributed via Hugging Face and ModelScope
What it needs
- Needs PyTorch, Transformers, LightLLM (production serving), LightX2V (production serving), gguf and diffusers (optional GGUF)
- Models: SenseNova-U1.5-8B-MoT, SenseNova-U1-8B-MoT, SenseNova-U1-A3B-MoT, safetensors LoRA, GGUF Q8
Quick answers
Is sensenova-u1 open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Can you run sensenova-u1 with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Open models
See all 52| Rank | Project | Score |
|---|---|---|
| 1 | ruviewWiFi CSI sensing on ESP32 for presence, breathing, heart rate and pose | 95 out of 100 |
| 2 | llmfitRust tool that checks which LLMs fit your RAM, CPU and GPU | 87 out of 100 |
| 3 | layaSingle-pass multilingual classifier for typed choice, score and yes/no decisions | 86 out of 100 |
| #4 | timesfmPretrained time-series foundation model for zero-shot forecasting from Google Research | 77 out of 100 |
| #5 | yolov5PyTorch YOLOv5 object detection, segmentation and classification models with training code | 75 out of 100 |