Minjia Zhang, Zhen Zhu, Yiming Gong
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.
| Repository | Role | Ran |
|---|---|---|
| Supercomputing-System-AI-Lab/InstantEdit | canonical | 3 of 11 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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
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.