FastVideo is a framework for training and running accelerated video-generation models, including real-time inference and post-training workflows. It is for researchers and developers building or deploying diffusion-based systems that generate video.
Borrowing it
Nothing to install: this file belongs to hao-ai-lab/FastVideo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hao-ai-lab/FastVideo/main/.agents/skills/seed-ssim-references/SKILL.mdgit clone --depth 1 https://github.com/hao-ai-lab/FastVideoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/hao-ai-lab/fastvideo/seed-ssim-references)<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/seed-ssim-references"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/seed-ssim-references/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hao-ai-lab/fastvideo/seed-ssim-references"><img src="https://agentmods.dev/badge/skills/hao-ai-lab/fastvideo/seed-ssim-references.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00146 | $0.04909 |
| Opus 5 | $0.00073 | $0.02455 |
| Sonnet 5 | $0.00029 | $0.00982 |
| Haiku 4.5 | $0.00015 | $0.00491 |
Grade A, and why
seed-ssim-references scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seed SSIM Reference Artefacts (mp4 or pt)
Purpose
A brand-new SSIM test in fastvideo/tests/ssim/ fails forever until its
reference artefacts exist on the HF dataset
(FastVideo/ssim-reference-videos). The dataset hosts two kinds of artefacts
side-by-side per (model_id, backend, prompt):
.mp4— pixel ground-truth for tests that callrun_text_to_video_similarity_test/run_image_to_video_similarity_testininference_similarity_utils.py. Compared via SSIM..pt— pre-VAE latent bundle (fp16 full latent + fp32 slice + metadata +slice_spec+format_version) for tests that callrun_text_to_latent_similarity_testinlatent_similarity_utils.py. Compared via cosine distance on the slice and the full tensor.
This skill:
- Detects which artefact type the test produces (pixel vs latent).
- Runs the test on Modal's L40S pool to generate the artefacts.
- Downloads them to the local repo via
modal volume get. - Pauses so the user can verify quality:
- mp4: visual eyeball in a video player.
- pt: numerics dump (shape, slice stats, NaN/Inf check, metadata).
- Uploads only the new test's files to HF, with a guard that refuses to overwrite anything already present.
The skill is run manually, once per new test. Before invoking it, the user
has already sanity-tested the new test locally — it launches VideoGenerator
and writes an artefact without crashing (the missing-reference assertion at
the end is expected). The skill does not re-test locally; it goes straight
to the manual legacy Modal L40S reference-maintenance target. Active CI runs
on the Slinky Slurm cluster and only consumes the resulting references.
When to use
- A new
test_*_similarity.pyfile has been added infastvideo/tests/ssim/and the HF dataset has noreference_videos/default/L40S_reference_videos/<model_id>/subtree for it yet.
When not to use
- Regular CI runs — once refs exist,
pytest fastvideo/tests/ssim/downloads them automatically. - Re-seeding an existing test. That requires
--forceon the upload step, and is out of scope here; treat as a separate, deliberate operation.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 381 lines · 146 tokens per session scan A 3c1111e2d213
seed-ssim-references is a skill published in the GitHub repository hao-ai-lab/FastVideo (4,368 stars, last pushed 2d ago), licensed Apache-2.0. It adds 146 tokens to every session and 4,909 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
testing
Writing frontend tests for the nvcf-ui app — Vitest, Testing Library, MSW, and project-specific render helpers. Use when creating test files, writing component tests, setting up MSW handlers in tests, deciding which render helper to use, or when the user is adding or modifying a UI component and hasn't mentioned tests…
diffusers-ascend-pipeline
A guide for running image and video generation pipelines on Huawei Ascend NPUs with the Diffusers library. Diffusers is a software library for using generative models, and the guide covers model pipelines, memory settings, LoRA adapters, and multi-card inference.
migrate-xunit-to-xunit-v3
Migrate .NET test projects from xUnit.net v2 to xunit.v3 and fix v3 breaks. Use for package/CPM conversion, OutputType=Exe, preserving the VSTest or MTP runner (including projects currently using YTest.MTP.XUnit2), incompatible TFMs, async void tests, string-to-Type attributes, custom Fact/Theory/BeforeAfterTest…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
nw-fp-clojure
Clojure language-specific patterns, data-first modeling, REPL-driven development, and spec.
mobiai-ios-testing
Use when writing or running tests in an iOS project — unit tests, UI tests, snapshot tests, choosing the right framework.