Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911897002967040 |
|---|---|
| author | Gu, Jiatao Shen, Ying Zhai, Shuangfei Zhang, Yizhe Jaitly, Navdeep Susskind, Joshua M. |
| author_facet | Gu, Jiatao Shen, Ying Zhai, Shuangfei Zhang, Yizhe Jaitly, Navdeep Susskind, Joshua M. |
| contents | Diffusion models have emerged as a powerful tool for generating high-quality images from textual descriptions. Despite their successes, these models often exhibit limited diversity in the sampled images, particularly when sampling with a high classifier-free guidance weight. To address this issue, we present Kaleido, a novel approach that enhances the diversity of samples by incorporating autoregressive latent priors. Kaleido integrates an autoregressive language model that encodes the original caption and generates latent variables, serving as abstract and intermediary representations for guiding and facilitating the image generation process. In this paper, we explore a variety of discrete latent representations, including textual descriptions, detection bounding boxes, object blobs, and visual tokens. These representations diversify and enrich the input conditions to the diffusion models, enabling more diverse outputs. Our experimental results demonstrate that Kaleido effectively broadens the diversity of the generated image samples from a given textual description while maintaining high image quality. Furthermore, we show that Kaleido adheres closely to the guidance provided by the generated latent variables, demonstrating its capability to effectively control and direct the image generation process. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_21048 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling Gu, Jiatao Shen, Ying Zhai, Shuangfei Zhang, Yizhe Jaitly, Navdeep Susskind, Joshua M. Computer Vision and Pattern Recognition Diffusion models have emerged as a powerful tool for generating high-quality images from textual descriptions. Despite their successes, these models often exhibit limited diversity in the sampled images, particularly when sampling with a high classifier-free guidance weight. To address this issue, we present Kaleido, a novel approach that enhances the diversity of samples by incorporating autoregressive latent priors. Kaleido integrates an autoregressive language model that encodes the original caption and generates latent variables, serving as abstract and intermediary representations for guiding and facilitating the image generation process. In this paper, we explore a variety of discrete latent representations, including textual descriptions, detection bounding boxes, object blobs, and visual tokens. These representations diversify and enrich the input conditions to the diffusion models, enabling more diverse outputs. Our experimental results demonstrate that Kaleido effectively broadens the diversity of the generated image samples from a given textual description while maintaining high image quality. Furthermore, we show that Kaleido adheres closely to the guidance provided by the generated latent variables, demonstrating its capability to effectively control and direct the image generation process. |
| title | Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2405.21048 |