Post
23
Jeveration draws a 512x512 image in 77.8 ms with a single forward pass of a frozen Qwen3.5-4B. That is up to 122x faster than Janus-Pro-7B (9,508 ms), at 0.74 GenEval vs its 0.80.
Autoregressive and diffusion models need many sequential evaluations per image. Here all 128 image codes are decided in parallel, conditioned on one shared random state so they fit together. Only rank-256 LoRA adapters and output heads are trained. The same checkpoint also does image-to-image and dense prediction.
š How it works
⢠Phase 1: a masked model learns the code distribution. Alone, it reaches only 0.32 GenEval in one pass
⢠Phase 2: Di[M]O-style distribution matching plus a correction target trains the one-pass model
⢠Fixed state instead of random: GenEval 0.73 to 0.70, HPSv2.1 28.27 to 26.63
š The numbers
⢠Show-o Turbo-512 (4 steps): 0.63 GenEval, 94.1 ms. Jeveration: 0.74, 77.8 ms
⢠Image-to-image at 91.7 ms per request; NYUv2 segmentation 67.7 mIoU vs 53.5 for DeepLabV3+
⢠Joint training vs text-to-image only: GenEval 0.74 vs 0.73
ā ļø Caveats
⢠DPG 78.24 trails FLUX.1-schnell (85.97) and Janus-Pro-7B (83.91)
⢠Dense training is NYUv2 indoor only; normals lag (24.2 vs 21.2 degrees)
⢠Latency is one H200 at batch 1; the repo has inference code only; not independently reproduced
Weights are 6.5 GB, Apache-2.0:
hf download linlinlinlinsdada/Jeveration --local-dir weights
Jeveration: System One Models Now Generate (2611.24738)
https://github.com/Carol-lyh/Jeveration
If you run a few-step generator today, would 78 ms at 0.74 GenEval beat it for your latency budget?
š Read it elsewhere
⢠The deep dive on Medium: https://medium.com/p/e129423fab53
⢠The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/jeveration-a-frozen-qwen35-4b-draws
⢠The thread on X: https://x.com/saavoji/status/2123847044502864155
⢠Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#jeveration-makes
Autoregressive and diffusion models need many sequential evaluations per image. Here all 128 image codes are decided in parallel, conditioned on one shared random state so they fit together. Only rank-256 LoRA adapters and output heads are trained. The same checkpoint also does image-to-image and dense prediction.
š How it works
⢠Phase 1: a masked model learns the code distribution. Alone, it reaches only 0.32 GenEval in one pass
⢠Phase 2: Di[M]O-style distribution matching plus a correction target trains the one-pass model
⢠Fixed state instead of random: GenEval 0.73 to 0.70, HPSv2.1 28.27 to 26.63
š The numbers
⢠Show-o Turbo-512 (4 steps): 0.63 GenEval, 94.1 ms. Jeveration: 0.74, 77.8 ms
⢠Image-to-image at 91.7 ms per request; NYUv2 segmentation 67.7 mIoU vs 53.5 for DeepLabV3+
⢠Joint training vs text-to-image only: GenEval 0.74 vs 0.73
ā ļø Caveats
⢠DPG 78.24 trails FLUX.1-schnell (85.97) and Janus-Pro-7B (83.91)
⢠Dense training is NYUv2 indoor only; normals lag (24.2 vs 21.2 degrees)
⢠Latency is one H200 at batch 1; the repo has inference code only; not independently reproduced
Weights are 6.5 GB, Apache-2.0:
hf download linlinlinlinsdada/Jeveration --local-dir weights
Jeveration: System One Models Now Generate (2611.24738)
https://github.com/Carol-lyh/Jeveration
If you run a few-step generator today, would 78 ms at 0.74 GenEval beat it for your latency budget?
š Read it elsewhere
⢠The deep dive on Medium: https://medium.com/p/e129423fab53
⢠The long read on Substack: https://sajjadpakdamansavoji.substack.com/p/jeveration-a-frozen-qwen35-4b-draws
⢠The thread on X: https://x.com/saavoji/status/2123847044502864155
⢠Every version on sajjadpsavoji.github.io: https://sajjadpsavoji.github.io/blog#jeveration-makes