Jeveration: System One Models Now Generate
Paper • 2611.24738 • Published • 148
ONNX export of Jeveration text-to-image for ONNX Runtime Web (WebGPU). Jeveration generates a 512 x 512 image in one forward pass of a Qwen3.5-4B backbone, so it runs in the browser without a denoising loop.
Demo: linoyts/Jeveration-WebGPU
assets/prompt_template.json) and is embedded (embed_tokens_q4f16.onnx).assets/) and embedded (decision_embed_fp16.onnx).backbone_int8/chunk_0..7.onnx, 4 layers each). The decision
tokens attend to each other in both directions.head_fp16.onnx); all
128 codes are sampled at once.clip_text_fp16.onnx) into the image (decoder_fp16.onnx).| File | Precision | Size |
|---|---|---|
backbone_int8/chunk_*.onnx |
int8 weights (MatMulNBits, block 32), LoRA merged | 8 x 0.5 GB |
head_fp16.onnx |
fp16 | 0.96 GB |
decoder_fp16.onnx |
fp16 | 0.61 GB |
embed_tokens_q4f16.onnx |
int4 table (from onnx-community/Qwen3.5-4B-ONNX) | 0.37 GB |
clip_text_fp16.onnx |
fp16 | 0.25 GB |
decision_embed_fp16.onnx |
fp16 | 0.03 GB |
All graphs take and return fp32. The linear-attention (Gated DeltaNet) layers use a chunked form made of matmuls, with
no Scan or Loop nodes.
Checked against the official PyTorch pipeline (bf16, same random draws) on 4 prompts, with ONNX Runtime on CPU:
Apache-2.0, as the original Jeveration weights. The backbone is derived from Qwen/Qwen3.5-4B, the decoder from TA-TiTok and the text tower from OpenAI CLIP ViT-L/14-336; each keeps its own license.
@article{liu2026jeveration,
title = {Jeveration: System One Models Now Generate},
author = {Liu, Yuhe and Li, Qi and Zhang, Shihua and Wang, Xinchao},
journal = {arXiv preprint arXiv:2611.24738},
year = {2026}
}