跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 4 天前AI 評分45

Jeveration:System One 模型現可生成圖像

Jeveration: System One Models Now Generate

AI 導讀

Jeveration 將凍結的視覺語言模型改作生成模型,讓 System One 模型以單次前向傳播生成連貫圖像,並支援圖像轉圖像及密集預測。模型生成 512x512 圖像需時 78 ms,速度最高比現有統一模型快 122x。實驗顯示,其圖像質素及密集預測效能具競爭力。

正文

Published on Nov 18

·

Submitted by

liu

on Nov 19

Authors:

,

,

Abstract

Jeveration repurposes a frozen vision-language model to generate coherent images and perform image-to-image and dense prediction tasks in a single forward pass with fast 512x512 generation.

System One models such as Jev return decisions through fast, parallel prediction. In this paper, we introduce Jeveration, showing that the same decision paradigm can also generate high-quality images in a single forward pass. Jeveration builds on a frozen vision-language model, repurposing its visual-semantic knowledge for holistic image generation. The key challenge is to maintain global consistency. A single prompt admits many valid images, yet parallel predictions must converge on a coherent whole. We therefore condition all positions on a shared random state to coordinate parallel predictions, so that each draw yields a different but coherent image. Since the model tends to ignore this state under direct image supervision, we first learn a distribution over discrete image codes to guide single-pass generation. Beyond text-to-image generation, we further unify image-to-image generation and dense prediction within the same architecture, so that one checkpoint supports all three tasks, each in one forward pass. Experiments show that Jeveration generates a 512x512 image in 78 ms, up to 122x faster than existing unified models, while maintaining competitive image quality and dense prediction performance.

View arXiv page View PDF Add to collection

Get this paper in your agent:

hf papers read 2611.24738

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.24738 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.24738 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.24738 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co