Model reference · open weights
SenseNova-U1.5-MoT is an open-weight language model from sensenova, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
SenseNova-U1.5-8B-MoT Overview SenseNova-U1.5-8B-MoT is our latest native unified multimodal checkpoint for more accurate, consistent, reliable, and aesthetically compelling visual creation. Built on NEO-unify, it strengthens the patchify layers, data quality and distribution, task formulation, prompt enhancement, and post-training pipeline. The official release focuses on six user-visible improvements: - Higher-quality image generation: improved composition and color harmony, with more realistic material rendering, natural lighting, stronger visual fidelity, and finer local details. - Better text rendering and infographic generation: more legible Chinese and English text, with clearer information hierarchy in posters, infographics, brand assets, and other text-dense designs. - More efficient native 4K generation: more coherent global structure, color harmony, and stable high-resolution output with improved generation efficiency. - More reliable native image editing: stronger preservation of subject identity and unedited content across local, text, multi-reference, insertion, and replacement edits. - Stronger complex-instruction following: more consistent execution of object counts, spatial relationships, layouts, styles, and multiple constraints within a single request. - More precise visual control: more accurate region- and object-level control through bounding boxes, visual markers, and single- or multi-image references. Showcases Key Benchmarks Quick Start The reference inference implementation is available in the SenseNova-U1 GitHub repository. Installation The upstream environment uses Python 3.11, PyTorch 2.8, and CUDA 12.8. For other CUDA versions and optional FlashAttention configurations, see the installation guide. Text-to-Image Image Editing See the inference examples for more options, supported resolutions, and batch processing. Best Practices Direct natural-language prompts work well for clear tasks with few constraints. For complex generation or editing, use prompt enhancement when additional planning is needed and explicitly specify what should remain unchanged. See the SenseNova-U1.5 Cookbook for setup instructions and optional Image PE, Captio
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | sensenova |
|---|---|
| Type | Language models |
| Parameters (lead) | 17.5B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-08-19 |
| Popularity | 6k downloads / month |
| Likes | 196 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| SenseNova-U1.5-8B-MoT | 17.5B | BF16 | ~40.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys sensenova-u1-5-mot for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (sensenova-u1-5-mot below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"sensenova-u1-5-mot","messages":[{"role":"user","content":"Hello"}]}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗