infinite-image-browsing
A full-featured image/video management app with AI-powered organization and semantic search. Supports metadata from SD-webui, ComfyUI, Fooocus, NovelAI, StableSwarmUI, and more. Available as standalone app, SD-webui extension, or library.
Runssource: GitHubPythonMITcommit 67ce3a77c4be
Python, MIT licensed. The project labels itself: audio, comfyui, extension, file explorer, file server, fooocus, gallery and image previewer.
infinite-image-browsing runs. An Argusic agent installed it in 20 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 IIB standalone server installs cleanly in a venv and runs python app.py on port 8770, serving the UI at / (200), the API hello (200), indexed image search (4 images found), thumbnails, video streaming, and video covers, with only the optional hnswlib topic-clustering dependency missing.
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 100 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.
- av==14.4.0 has no cp312 binary wheel and its sdist build needs ffmpeg dev headers (not installed, no root)8 minutes
- install.py crashed: ModuleNotFoundError: No module named 'launch'7 minutes
- hnswlib has no cp312 binary wheel and its sdist build needs Python.h/C++ toolchain (not installed, no root)5 minutes
- System Python is PEP 668 externally-managed; pip install failed without sudo2 minutes
- Install time
- 20 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- pip install -r requirements.txt exited 0 in fresh venv; python install.py printed 0 errors; python app.py --port 8770 started; curl / -> 200, hello -> "hello"; image-thumbnail 200 + PIL decode PNG 64x48; stream_video 200 + ffmpeg -v error -i -f null decode OK; video_cover 200 + WebP decode 160x120; db/basic_info img_count 4; search_by_substr surstr=clip returned clip.mp4
- Model tokens used
- 629,342
- Exact commit tested
- 67ce3a77c4be
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
629,342 All done. Final report: **What I did** - Read the README (standalone Python mode: `python app.py`). - Installed deps in a fresh venv, fixed 4 install-path errors, and verified the app end-to-end agai… - Changes kept minimal: new `launch.py`, `av` pin in `requirements.txt`, `.venv` in `.gitignore`. **Verified facts (all observed)** - Fresh venv `pip install` exited 0; `install.py` printed 0 errors. - `python app.py --port 8770 --extra_paths /tmp/iib_images` started, `GET /` → 200 HTML, `hello` → … - Thumbnail 200 + PIL-decode OK (PNG 64×48); `stream_video` 200 + `ffmpeg -v error` full decode OK;… - Index/search worked: `img_count=4`, `surstr=clip` returned `clip.mp4`, tag match for Video return… - `hnswlib` (optional per project; only gates experimental topic clustering) could not be built — n…
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
- Reached a running state on a clean machine, with the session recorded.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Took 20 minutes to install, slower than the median of the 11 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 12 audio projects Argusic has installed and timed, infinite-image-browsing was the 9th fastest to reach a running state, and 10 of 12 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
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
Topics (from GitHub)
audiocomfyuiextensionfile-explorerfile-serverfooocusgalleryimage-previewernovelaipreviewerremote-explorerskillsstable-diffusion-webuistable-diffusion-webui-pluginstable-swarm-uistableswarmuivideovideo-player
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/infinite-image-browsing)Questions
- Does infinite-image-browsing run?
- Yes. infinite-image-browsing runs. Argusic installed and launched it on a clean machine in 20 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test infinite-image-browsing?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 67ce3a77c4be. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test infinite-image-browsing?
- The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does infinite-image-browsing take to install?
- 20 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 infinite-image-browsing need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing infinite-image-browsing?
- 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.
- How does infinite-image-browsing compare with the alternatives?
- Of the 12 audio projects Argusic has installed and timed, infinite-image-browsing was the 9th fastest to reach a running state, and 10 of 12 reached one at all.
- Where is the evidence for infinite-image-browsing?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.