SSyncDev

SenseNova-U1.5-8B-MoT

SyncDev model directory · Profile updated Nov 18, 2026

Compare with another model

SenseNova-U1.5-8B-MoT is SenseTime's open unified model for native 4K image generation and instruction-based image editing, Apache-2.0 licensed.

Key specifications

Specification score
14.5
License
Apache-2.0

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: No API pricing stated; open weights for self-hosting

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input
  • Image input

Produces

  • Text output
  • Image output

Capabilities

VisionOpen weights

What is SenseNova-U1.5-8B-MoT?

Posters break most image models. Small Chinese captions turn to noise, the hierarchy collapses, and a second round of edits quietly changes the face you asked it to keep. SenseNova-U1.5-8B-MoT is SenseTime's August 2026 answer to exactly those failures, and it ships as open weights.

It is a native unified multimodal checkpoint built on SenseTime's NEO-unify design: one model reads text and images and generates images, rather than a language model bolted to a separate diffusion decoder. U1.5 rebuilds the patchify layers, the data mix, the task formulation, prompt enhancement and post-training of the earlier U1.

What actually improved

  • Native generation up to 4K, with steadier global structure at high resolution.
  • Legible English and Chinese text in infographics, posters and brand assets.
  • Editing that keeps identity and untouched regions intact across local, text, multi-reference, insertion and replacement edits.
  • Instructions with counts, spatial relations and several constraints at once.
  • Region control through bounding boxes, visual markers and one or more reference images.

Checkpoints and adapters

Checkpoint What it is
sensenova/SenseNova-U1.5-8B-MoT Main RL-tuned release
SenseNova-U1.5-8B-MoT-SFT Supervised stage only
SenseNova-U1.5-8B-MoT-TailSteer 4 November 2026, steadier multi-turn editing
U1.5 LoRAs 8-step adapter (August) and an 8-step V2 (24 September)

The weights total roughly 17.5B parameters on disk, despite the "8B" in the name. Reference code runs on Python 3.11, PyTorch 2.8 and CUDA 12.8. The Hub repository is dated 19 August while the project's own release log says 20 August; either way, it is the same checkpoint.

Limits worth planning for

SenseTime is candid about weak spots. Colours can oversaturate (lowering cfg_scale helps). Dense, tiny or mixed-language text still slips. Exact counts in tight layouts, small hands and faces, and long multi-reference editing sessions can drift. That last point is why TailSteer exists.

A practical trial

Take twenty briefs your designers actually received last month. Generate each at 2048×2048, then run three rounds of edits that must preserve a face or a logo, and score drift per round. Compare it against a hosted option such as Qwen-Image-2.1-Pro and the rest of the text-to-image directory. If multi-turn stability is your bottleneck, rerun the editing rounds with TailSteer before you decide. A free browser playground, SenseNova-Studio, lets non-engineers judge output before anyone provisions a GPU.

How to evaluate SenseNova-U1.5-8B-MoT

Compare the model on the work you need to complete.

Tasks and inputs

SenseNova-U1.5-8B-MoT is listed for Any-to-any, Image-to-image, Text-to-image. It accepts text, image and produces text, image. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Choose the output size and quality your design needs. Include drafts and revisions when budgeting an accepted image.

Choosing a deployment

The weights are downloadable under Apache-2.0. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

Yes. The weights are on Hugging Face under Apache-2.0, with reference inference code in the SenseNova-U1 project.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

Liquid AI

LFM3-Omni-2B

LFM3-Omni-2B is Liquid AI's open any-to-any model: image, video, audio and text in; text and speech out, with multimodal tool calls on-device.

— context

NVIDIA

Nemotron-Labs-Diffusion-Uni-8B

NLD-Uni (Nemotron-Labs-Diffusion-Uni-8B) is NVIDIA's open diffusion-language model that both understands images and generates them, for research.

— context

NVIDIA

PixelUMM

PixelUMM is NVIDIA's encoder-free 15B unified model that understands and generates text, images and video directly in pixel space. Non-commercial.

— context

shanghai-ai-lab

InternLumina-U2

InternLumina-U2 is Shanghai AI Lab's masked-diffusion MoE that understands images, video and 3D and generates and edits images with 8-codebook visual tokens.

— context

Tencent

Hy-Embodied-RxBrain-1.0

Hy-Embodied-RxBrain-1.0 is Tencent's 6.2B embodied model that reasons in text and imagines goal images, for planning, world-state prediction and video QA.

— context

google

google/gemma-4-E2B-it

google/gemma-4-E2B-it is a source-linked Hugging Face repository assigned to Any-to-any. Its recorded task interface accepts text, image, audio, video and produces text, image, audio, video.

131.07K context