SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2508.06033 · ICCV · 2025

InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow

Minjia Zhang, Zhen Zhu, Yiming Gong

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 11 functions out of this paper's own repositories and ran 3 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
Supercomputing-System-AI-Lab/InstantEdit canonical 3 of 11
FunctionStatusWhere it lives
betas_for_alpha_bar Ran Supercomputing-System-AI-Lab/InstantEdit/src/scheduler_perflow.py
pointer only (licence: NONE) · get_code("f1e3f7493aad4745")
get_word_inds Ran Supercomputing-System-AI-Lab/InstantEdit/utils_/ptp_utils.py
pointer only (licence: NONE) · get_code("90914e1d22798d8a")
retrieve_timesteps Ran Supercomputing-System-AI-Lab/InstantEdit/src/pipeline.py
pointer only (licence: NONE) · get_code("3338a5b299ea25ec")
calculate_metric Not yet run Supercomputing-System-AI-Lab/InstantEdit/pie_evaluator/evaluate.py
pointer only (licence: NONE) · get_code("608cb84fa52efd4c")
get_matrix Not yet run Supercomputing-System-AI-Lab/InstantEdit/utils_/seq_aligner.py
pointer only (licence: NONE) · get_code("d167441d997c52ce")
get_matrix Not yet run Supercomputing-System-AI-Lab/InstantEdit/utils_/seq_aligner.py
pointer only (licence: NONE) · get_code("81db21bf982ca0fe")
get_traceback_matrix Not yet run Supercomputing-System-AI-Lab/InstantEdit/utils_/seq_aligner.py
pointer only (licence: NONE) · get_code("beb8f6a30678a4d9")
register_attention_control Not yet run Supercomputing-System-AI-Lab/InstantEdit/utils_/ptp_utils.py
pointer only (licence: NONE) · get_code("169aabcc919f06d9")
retrieve_latents Not yet run Supercomputing-System-AI-Lab/InstantEdit/src/sd_inversion_pipeline.py
pointer only (licence: NONE) · get_code("d71bb2e5331b74e2")
rle2mask Not yet run Supercomputing-System-AI-Lab/InstantEdit/instantedit.py
pointer only (licence: NONE) · get_code("3fa3967a4213827d")
update_alpha_time_word Not yet run Supercomputing-System-AI-Lab/InstantEdit/utils_/ptp_utils.py
pointer only (licence: NONE) · get_code("5d75f6c0e6788bf7")

Repositories linked to this paper

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

Abstract

We propose a fast text-guided image editing method called InstantEdit based on the RectifiedFlow framework, which is structured as a few-step editing process that preserves critical content while following closely to textual instructions. Our approach leverages the straight sampling trajectories of RectifiedFlow by introducing a specialized inversion strategy called PerRFI. To maintain consistent while editable results for RectifiedFlow model, we further propose a novel regeneration method, Inversion Latent Injection, which effectively reuses latent information obtained during inversion to facilitate more coherent and detailed regeneration. Additionally, we propose a Disentangled Prompt Guidance technique to balance editability with detail preservation, and integrate a Canny-conditioned Con-trolNet to incorporate structural cues and suppress artifacts. Evaluation on the PIE image editing dataset demonstrates that InstantEdit is not only fast but also achieves better qualitative and quantitative results compared to stateof-the-art few-step editing methods. Our code is available here: https://github.com/Supercomputing-System-AI-Lab/InstantEdit

For agents

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

get_harvested_code_for_paper("2508.06033")
get_code_for_paper("2508.06033")
have("2508.06033")

Connect an agent — have() is free.