Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"
active 2024-12-11 → 2026-05-27 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 533 days from 2024-12-11 to 2026-05-27. Pushes: 16 total, peak 3 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 42 total, peak 3 in a day. Comments: 39 total, peak 4 in a day. Stars: 724 total, peak 41 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| matankleiner | 46 | 14 | 0 | 16 |
| nktoan | 4 | 0 | 0 | 3 |
| BoBo0037 | 4 | 0 | 0 | 1 |
| dejian-lc | 3 | 0 | 0 | 2 |
| fallenshock | 3 | 2 | 0 | 1 |
| zhaozhaoooo | 2 | 0 | 0 | 0 |
| HarlayZhang | 2 | 0 | 0 | 1 |
| Oguzhanercan | 2 | 0 | 0 | 1 |
| EmmaThompson123 | 2 | 0 | 0 | 0 |
| zhang2002forwin | 2 | 0 | 0 | 2 |
| ankitagr01 | 2 | 0 | 0 | 1 |
| swn233 | 2 | 0 | 0 | 2 |
| moclimb | 2 | 0 | 0 | 0 |
| wanluzhu | 1 | 0 | 0 | 0 |
| Muawizodux | 1 | 0 | 0 | 0 |
| Hakurei-Reimu-Gensokyo | 1 | 0 | 0 | 0 |
| yijiaguo02 | 1 | 0 | 0 | 1 |
| KyujinHan | 1 | 0 | 0 | 0 |
| Niklas-Penzel | 1 | 0 | 0 | 0 |
| tiga-dudu | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#28fadingecho2026-01-28 11:24Any plan to support qwen-image-edit model?
- Issue comment#15swn2332025-12-28 13:24Request for Baseline ODE Inv. Code
- Issue comment#25swn2332025-12-28 13:17Get inbetween states?
- Issue#23matankleiner2025-12-18 09:32FlowEdit + WAN2.1 = Awesome Video Editing
- Issue#26Hakurei-Reimu-Gensokyo2025-12-16 07:58the flux pipeline gives out unexpected result.
- Issue comment#12matankleiner2025-12-04 06:44ODE inversion
- Issue comment#12tairuisecret2025-12-03 13:35ODE inversion
- Issue#25Niklas-Penzel2025-11-06 15:43Get inbetween states?
- Issue#24ViviranZ2025-11-02 08:18Questions about training setup and code release
- Issue comment#4RC-Wu2025-09-21 10:35RuntimeError: The size of tensor a (4608) must match the size of tensor b (1536) at non-singleton dimension 2
- Issue#23KyujinHan2025-08-29 14:42FlowEdit + WAN2.1 = Awesome Video Editing
- Issue#20matankleiner2025-08-28 13:46about flowedit in Wan2.1
- Issue comment#21matankleiner2025-08-18 09:17GPU VRAM requirement ?
- Issue comment#22matankleiner2025-08-18 09:15Lack of the prompts for skyline
- Issue#22matankleiner2025-08-18 09:15Lack of the prompts for skyline
- Issue#21wanluzhu2025-08-06 14:12GPU VRAM requirement ?
- Issue#20zhaozhaoooo2025-08-06 11:56about flowedit in Wan2.1
- Issue#19liushanyuan182025-07-25 10:00Questions about noise sampling
- Issue comment#18matankleiner2025-07-01 09:44About Wan + flowedit
- Issue#18matankleiner2025-07-01 09:44About Wan + flowedit
- Issue#18zhaozhaoooo2025-06-27 11:44About Wan + flowedit
- Issue#17EmmaThompson1232025-06-03 05:20Why is `zt_edit = zt_edit + (t_im1 - t_i) * V_delta_avg` instead of `zt_edit = zt_edit + t_i * V_delta_avg`
- Issue#17EmmaThompson1232025-06-03 04:06Why is `zt_edit = zt_edit + (t_im1 - t_i) * V_delta_avg` instead of `zt_edit = zt_edit + t_i * V_delta_avg`
- Issue comment#15nktoan2025-04-14 02:59Request for Baseline ODE Inv. Code
- Issue comment#14matankleiner2025-04-13 06:40pipe = FluxPipeline.from_pretrained(model_id_flux, torch_dtype=torch.float16, return_dict=False) AttributeError: 'str' object has no attribute 'from_pretrained'
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 724 stars here means stars gained during the window, not the repo's star count.