ID-V2V

The official implementation of SIGGRAPH Asia 2026 paper "ID-V2V: Identity-preserving Video Restylization"

Runs with mockssource: GitHubhomepagePythonApache-2.0commit b9df1e501b25

Python, Apache-2.0 licensed. The project labels itself: controllable generation, relighting, video editing, video generation, video to video, videoediting and videogeneration.

ID-V2V runs, with stand-ins for the services it depends on. An Argusic agent installed it in 55 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

The repo installs and its preprocessing/save pipeline runs on CPU against the bundled sample media, with the SAM3 gated checkpoints and GPU needed for a real model run.

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 71 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
71 / 100
cost of the verifying run
$0.14 (measured)
recorded runs
2
last tested
stars
296
forks
31
open issues
1
watchers
2
size
197 MB
created
last push

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.

Time lost to each failure while testing ID-V2V, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • pack_per_frame_instances crashed on SAM3 tracker outputs lacking scores/boxes or with per-object (H,W) masks (KeyError/shape errors)14 minutes
  • save_sam3_per_frame_folders left empty frame folders without sam3Mask_id_all.png, which would break downstream orig_pixel9 minutes
  • uv was not installed in the container8 minutes
  • uv sync regenerated uv.lock (revision 3 to 5, cosmetic URL changes)2 minutes
Install time
55 minutes
Cold machine to finish
10 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
uv sync exited 0 (torch 2.6.0+cu118, transformers 5.9.0, flash-attn 2.7.1.post4 installed); ./.venv/bin/python /tmp/verify_suite.py printed ALL_VERIFY_SUITE_PASSED; 'python -m idv2v.preprocess.orig_pixel ...' exited 0 and decoded 81/81 frames with foreground kept and background grayed; preprocess.sh stops at the gated SAM3 checkpoint (checkpoints/sam3 missing).
Model tokens used
727,713
Exact commit tested
b9df1e501b25
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
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

727,713
All checks complete. Here is the mission report.
**What was verified**
- `uv sync` (README quickstart) completed cleanly in a Python 3.10.22 venv with `torch==2.6.0+cu118…
- Ran a verification suite on real bundled sample media (`test_samples/restylization/two_sitting_wo…
- The CLI path (`python -m idv2v.preprocess.orig_pixel ...` exactly as `preprocess.sh` invokes it) …
- `bash scripts/preprocess.sh` fails only at the first step with the error: `OSError: checkpoints/s…
- Found no project test suite (only sample data) — `pytest` is not configured anywhere in the repo.
**Errors encountered and fixes**
1. `pack_per_frame_instances` hard-crashed on SAM3 tracker outputs lacking `scores`/`boxes` (and on…
2. `save_sam3_per_frame_folders` left empty `frame_k/` folders without `sam3Mask_id_all.png`, which…
3. `uv.lock` was regenerated during `uv sync` (`revision 3 → 5` with cosmetic URL normalizations) —…

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 55 minutes.
  • Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed Apache-2.0, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs with mocks92.000.14
Argusic Runner1/3Did not run50.000.23

Topics (from GitHub)

controllable-generationrelightingvideo-editingvideo-generationvideo-to-videovideoeditingvideogeneration

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/ID-V2V.svg)](https://argusic.com/subject/id-v2v)

Questions

Does ID-V2V run?
ID-V2V runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 55 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test ID-V2V?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit b9df1e501b25. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test ID-V2V?
The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does ID-V2V take to install?
55 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 ID-V2V need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing ID-V2V?
4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for ID-V2V?
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.

Discussion