Kiwi-Edit
A unified and fully open-source framework for instruction-guided and reference-guided video editing using natural language.
Could not verifysource: GitHubhomepagePythonMITcommit 178f3f4f8221
Python, MIT licensed. The project labels itself: video editing and video generation.
Argusic could not get Kiwi-Edit running. An Argusic agent installed it in 8 minutes and hit 4 errors on a clean machine with no GPU, and the whole session was recorded.
Package builds and installs, core data loading/saving functions verified with demo files, but model inference requires CUDA GPU unavailable in this container.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 42.5 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- VideoData.__init__ crashed with TypeError: '<' not supported between instances of 'int' and 'NoneType'2 minutes
- huggingface-hub version conflict: transformers requires <1.0, datasets/diffusers require >=1.31.02 minutes
- Python 3.12 vs required 3.10, no conda available1 minute
- No CUDA GPU in container - cannot run model inference
- Install time
- 8 minutes
- Cold machine to finish
- 6 minutes
- Errors hit and fixed
- 4 hit, 3 fixed with no human help
- How the result was proved
- pip install -e . exited 0; python import diffsynth succeeded; VideoData(video_file=demo).raw_data() returned 101 valid frames; save_video wrote valid MP4 verified by ffmpeg; demo.py --help parsed; diffusers_demo.py --help parsed; WanVideoPipeline and ModelConfig importable
- Model tokens used
- 155,809
- Exact commit tested
- 178f3f4f8221
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Whether it works at all
- this run verified nothing, so this page makes no claim either way
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
**Install**: Created a Python 3.12 venv, installed torch 2.7.0+cpu (no GPU available), `pip install… **Bug found and fixed**: `VideoData.__init__` in `diffsynth/data/video.py` had a `min(length, len(s… **What works**: `VideoData` loads both video files (101 frames from the demo .mp4) and image files.… **Limitation**: No CUDA GPU in this container, so actual model inference cannot run. The project re… tokens used 155,809 Here's a summary of what I found and accomplished: ## Install & Verification Results **Install**: Created a Python 3.12 venv, installed torch 2.7.0+cpu (no GPU available), `pip install… **Bug found and fixed**: `VideoData.__init__` in `diffsynth/data/video.py` had a `min(length, len(s… **What works**: `VideoData` loads both video files (101 frames from the demo .mp4) and image files.… **Limitation**: No CUDA GPU in this container, so actual model inference cannot run. The project re…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 8 minutes.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- An agent with no time limit did not get it running.
- Hit 4 errors during setup, 1 of which were not solved.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Did not run | 45.00 | 0.03 | |
| Argusic Runner | 1/3 | Did not run | 40.00 | 0.04 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/kiwi-edit)Questions
- Does Kiwi-Edit run?
- Argusic could not verify that Kiwi-Edit runs. Argusic installed and launched it on a clean machine in 8 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test Kiwi-Edit?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 178f3f4f8221. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test Kiwi-Edit?
- The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Kiwi-Edit take to install?
- 8 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does Kiwi-Edit need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Kiwi-Edit?
- 4 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for Kiwi-Edit?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.