Search Results for author:
Found 20 papers, 11 papers with code
ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation
Both approaches lead to improved image quality when compared to monolithic models or generic, prompt-independent workflows.
DiffUHaul: A Training-Free Method for Object Dragging in Images
In this work, we propose a training-free method, dubbed DiffUHaul, that harnesses the spatial understanding of a localized text-to-image model, for the object dragging task.
LCM-Lookahead for Encoder-based Text-to-Image Personalization
In this work, we explore the potential of using such shortcut-mechanisms to guide the personalization of text-to-image models to specific facial identities.
Consolidating Attention Features for Multi-view Image Editing
In this work, we focus on spatial control-based geometric manipulations and introduce a method to consolidate the editing process across various views.
Training-Free Consistent Text-to-Image Generation
Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language.
Breathing Life Into Sketches Using Text-to-Video Priors
A sketch is one of the most intuitive and versatile tools humans use to convey their ideas visually.
Domain-Agnostic Tuning-Encoder for Fast Personalization of Text-To-Image Models
Text-to-image (T2I) personalization allows users to guide the creative image generation process by combining their own visual concepts in natural language prompts.
Key-Locked Rank One Editing for Text-to-Image Personalization
The task of T2I personalization poses multiple hard challenges, such as maintaining high visual fidelity while allowing creative control, combining multiple personalized concepts in a single image, and keeping a small model size.
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models
Specifically, we employ two components: First, an encoder that takes as an input a single image of a target concept from a given domain, e. g. a specific face, and learns to map it into a word-embedding representing the concept.
Cross-domain Compositing with Pretrained Diffusion Models
Diffusion models have enabled high-quality, conditional image editing capabilities.
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Yet, it is unclear how such freedom can be exercised to generate images of specific unique concepts, modify their appearance, or compose them in new roles and novel scenes.
Ranked #7 on
Personalized Image Generation
on DreamBooth
"This is my unicorn, Fluffy": Personalizing frozen vision-language representations
We propose an architecture for solving PerVL that operates by extending the input vocabulary of a pretrained model with new word embeddings for the new personalized concepts.
Ranked #24 on
Zero-Shot Composed Image Retrieval (ZS-CIR)
on CIRCO
State-of-the-Art in the Architecture, Methods and Applications of StyleGAN
Of these, StyleGAN offers a fascinating case study, owing to its remarkable visual quality and an ability to support a large array of downstream tasks.
Self-Conditioned Generative Adversarial Networks for Image Editing
We compare our models to a wide range of latent editing methods, and show that by alleviating the bias they achieve finer semantic control and better identity preservation through a wider range of transformations.
Stitch it in Time: GAN-Based Facial Editing of Real Videos
The ability of Generative Adversarial Networks to encode rich semantics within their latent space has been widely adopted for facial image editing.
HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing
In this work, we introduce this approach into the realm of encoder-based inversion.
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
Can a generative model be trained to produce images from a specific domain, guided by a text prompt only, without seeing any image?
LARGE: Latent-Based Regression through GAN Semantics
For modern generative frameworks, this semantic encoding manifests as smooth, linear directions which affect image attributes in a disentangled manner.
SWAGAN: A Style-based Wavelet-driven Generative Model
In recent years, considerable progress has been made in the visual quality of Generative Adversarial Networks (GANs).
Ranked #11 on
Image Generation
on FFHQ 1024 x 1024
MRGAN: Multi-Rooted 3D Shape Generation with Unsupervised Part Disentanglement
Our network encourages disentangled generation of semantic parts via two key ingredients: a root-mixing training strategy which helps decorrelate the different branches to facilitate disentanglement, and a set of loss terms designed with part disentanglement and shape semantics in mind.
