SenseNova-U1.5-8B-MoT

Text-to-image and image editing demo for sensenova/SenseNova-U1.5-8B-MoT, a natively unified multimodal model (18B params, bf16) built on the NEO-unify architecture.

Leave the image upload empty for text-to-image generation, or upload one or more images and write an edit instruction for image editing.

Advanced options exposes denoising steps, guidance scale, timestep shift, image guidance (editing) and the seed. The step count defaults to 28 rather than the model card's 50: a fixed-seed A/B found 28 keeps composition, prompt adherence and text rendering intact — losing only some micro-texture in landscape and skin, and nothing measurable when editing — while running ~1.8x faster. Raise it to 50 for detail-critical work.

Reference inference configuration (from the model card): cfg_scale=4.0, timestep_shift=3.0, num_steps=50.

Editing prompts are screened on CPU by hfmlsoc/ncii-guard-v02 before any GPU work is scheduled, to refuse requests to undress or sexualize a person in an uploaded photo.

The sensenova_u1 package is vendored locally to register the NEO-Unify model architecture with transformers. Running on ZeroGPU.