Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sinha, Animesh, Sun, Bo, Kalia, Anmol, Casanova, Arantxa, Blanchard, Elliot, Yan, David, Zhang, Winnie, Nelli, Tony, Chen, Jiahui, Shah, Hardik, Yu, Licheng, Singh, Mitesh Kumar, Ramchandani, Ankit, Sanjabi, Maziar, Gupta, Sonal, Bearman, Amy, Mahajan, Dhruv
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909333338456064
author Sinha, Animesh
Sun, Bo
Kalia, Anmol
Casanova, Arantxa
Blanchard, Elliot
Yan, David
Zhang, Winnie
Nelli, Tony
Chen, Jiahui
Shah, Hardik
Yu, Licheng
Singh, Mitesh Kumar
Ramchandani, Ankit
Sanjabi, Maziar
Gupta, Sonal
Bearman, Amy
Mahajan, Dhruv
author_facet Sinha, Animesh
Sun, Bo
Kalia, Anmol
Casanova, Arantxa
Blanchard, Elliot
Yan, David
Zhang, Winnie
Nelli, Tony
Chen, Jiahui
Shah, Hardik
Yu, Licheng
Singh, Mitesh Kumar
Ramchandani, Ankit
Sanjabi, Maziar
Gupta, Sonal
Bearman, Amy
Mahajan, Dhruv
contents We introduce Style Tailoring, a recipe to finetune Latent Diffusion Models (LDMs) in a distinct domain with high visual quality, prompt alignment and scene diversity. We choose sticker image generation as the target domain, as the images significantly differ from photorealistic samples typically generated by large-scale LDMs. We start with a competent text-to-image model, like Emu, and show that relying on prompt engineering with a photorealistic model to generate stickers leads to poor prompt alignment and scene diversity. To overcome these drawbacks, we first finetune Emu on millions of sticker-like images collected using weak supervision to elicit diversity. Next, we curate human-in-the-loop (HITL) Alignment and Style datasets from model generations, and finetune to improve prompt alignment and style alignment respectively. Sequential finetuning on these datasets poses a tradeoff between better style alignment and prompt alignment gains. To address this tradeoff, we propose a novel fine-tuning method called Style Tailoring, which jointly fits the content and style distribution and achieves best tradeoff. Evaluation results show our method improves visual quality by 14%, prompt alignment by 16.2% and scene diversity by 15.3%, compared to prompt engineering the base Emu model for stickers generation.
format Preprint
id arxiv_https___arxiv_org_abs_2311_10794
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression
Sinha, Animesh
Sun, Bo
Kalia, Anmol
Casanova, Arantxa
Blanchard, Elliot
Yan, David
Zhang, Winnie
Nelli, Tony
Chen, Jiahui
Shah, Hardik
Yu, Licheng
Singh, Mitesh Kumar
Ramchandani, Ankit
Sanjabi, Maziar
Gupta, Sonal
Bearman, Amy
Mahajan, Dhruv
Computer Vision and Pattern Recognition
We introduce Style Tailoring, a recipe to finetune Latent Diffusion Models (LDMs) in a distinct domain with high visual quality, prompt alignment and scene diversity. We choose sticker image generation as the target domain, as the images significantly differ from photorealistic samples typically generated by large-scale LDMs. We start with a competent text-to-image model, like Emu, and show that relying on prompt engineering with a photorealistic model to generate stickers leads to poor prompt alignment and scene diversity. To overcome these drawbacks, we first finetune Emu on millions of sticker-like images collected using weak supervision to elicit diversity. Next, we curate human-in-the-loop (HITL) Alignment and Style datasets from model generations, and finetune to improve prompt alignment and style alignment respectively. Sequential finetuning on these datasets poses a tradeoff between better style alignment and prompt alignment gains. To address this tradeoff, we propose a novel fine-tuning method called Style Tailoring, which jointly fits the content and style distribution and achieves best tradeoff. Evaluation results show our method improves visual quality by 14%, prompt alignment by 16.2% and scene diversity by 15.3%, compared to prompt engineering the base Emu model for stickers generation.
title Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.10794