SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.08258 · 2024

Improving Virtual Try-On with Garment-focused Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 7 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
siqi0905/gardiff canonical 7 of 8
FunctionStatusWhere it lives
FeedForward Ran siqi0905/gardiff/src/adapter/resampler.py
pointer only (licence: NONE) · get_code("5105747c2711b1cb")
betas_for_alpha_bar Ran siqi0905/gardiff/src/utils/DDIMSchdeduler.py
pointer only (licence: NONE) · get_code("f1e3f7493aad4745")
color_correction_func Ran siqi0905/gardiff/src/inf.py
pointer only (licence: NONE) · get_code("fd36b531307dbd5e")
rescale_zero_terminal_snr Ran siqi0905/gardiff/src/utils/DDIMSchdeduler.py
pointer only (licence: NONE) · get_code("6b47c0cd573d42ff")
reshape_tensor Ran siqi0905/gardiff/src/adapter/resampler.py
pointer only (licence: NONE) · get_code("4cb2e2a2ca0bec9f")
tokenize Ran siqi0905/gardiff/src/models/mask_attention.py
pointer only (licence: NONE) · get_code("534b549a2186b672")
tokenize_captions Ran siqi0905/gardiff/src/inf.py
pointer only (licence: NONE) · get_code("c29a833ec398ebd7")
prepare_fuse_mask Not yet run siqi0905/gardiff/src/inf.py
pointer only (licence: NONE) · get_code("b629ab0fcd8432e9")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Diffusion models have led to the revolutionizing of generative modeling in numerous image synthesis tasks. Nevertheless, it is not trivial to directly apply diffusion models for synthesizing an image of a target person wearing a given in-shop garment, i.e., image-based virtual try-on (VTON) task. The difficulty originates from the aspect that the diffusion process should not only produce holistically high-fidelity photorealistic image of the target person, but also locally preserve every appearance and texture detail of the given garment. To address this, we shape a new Diffusion model, namely GarDiff, which triggers the garment-focused diffusion process with amplified guidance of both basic visual appearance and detailed textures (i.e., high-frequency details) derived from the given garment. GarDiff first remoulds a pre-trained latent diffusion model with additional appearance priors derived from the CLIP and VAE encodings of the reference garment. Meanwhile, a novel garment-focused adapter is integrated into the UNet of diffusion model, pursuing local fine-grained alignment with the visual appearance of reference garment and human pose. We specifically design an appearance loss over the synthesized garment to enhance the crucial, high-frequency details. Extensive experiments on VITON-HD and DressCode datasets demonstrate the superiority of our GarDiff when compared to state-of-the-art VTON approaches. Code is publicly available at: \href{https://github.com/siqi0905/GarDiff/tree/master}{https://github.com/siqi0905/GarDiff/tree/master}.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.08258")
get_code_for_paper("2409.08258")
have("2409.08258")

Connect an agent — have() is free.