paper-with-me

Papers

Diffusion in Style

2023-01-01 · ICCV 2023 1 · Martin Nicolas Everaert, Marco Bocchio, Sami Arpa, Sabine Süsstrunk, Radhakrishna Achanta

We present Diffusion in Style, a simple method to adapt Stable Diffusion to any desired style, using only a small set of target images. It is based on the key observation that the style of the images generated by Stable Diffusion is tied to the initial latent tensor. Not adapting this initial latent tensor to the style makes fine-tuning slow, expensive, and impractical, especially when only a few target style images are available. In contrast, fine-tuning is much easier if this initial latent tensor is also adapted. Our Diffusion in Style is orders of magnitude more sample-efficient and faster. It also generates more pleasing images than existing approaches, as shown qualitatively and with quantitative comparisons.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer

2023-12-11 · CVPR 2024 1 · Jiwoo Chung, Sangeek Hyun, Jae-Pil Heo

Despite the impressive generative capabilities of diffusion models, existing diffusion model-based style transfer methods require inference-stage optimization (e.g. fine-tuning or textual inversion of style) which is tim…

Style Transfer

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion

2024-10-29 · Yu Zeng, Yang Zhang, Jiachen Liu, Linlin Shen 외

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many exi…

Image Generation

Diffusion-based Human Motion Style Transfer with Semantic Guidance

2024-03-20 · Lei Hu, Zihao Zhang, Yongjing Ye, Yiwen Xu 외

3D Human motion style transfer is a fundamental problem in computer graphic and animation processing. Existing AdaIN- based methods necessitate datasets with balanced style distribution and content/style labels to train …

Motion Style TransferStyle TransferTransfer Learning

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

2023-06-13 · NeurIPS 2023 11 · Yinghao Aaron Li, Cong Han, Vinay S. Raghavan, Gavin Mischler 외

In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs…

Speech Synthesistext-to-speechText to Speech

Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style

2023-01-01 · CVPR 2023 1 · Haoming Lu, Hazarapet Tunanyan, Kai Wang, Shant Navasardyan 외

Diffusion models have demonstrated impressive capability of text-conditioned image synthesis, and broader application horizons are emerging by personalizing those pretrained diffusion models toward generating some sp…

DisentanglementImage Generation