hao-ai-lab

19 mods across 1 repository, 4.2k stars between them.

add-model-01-prep

01

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use at the start of a FastVideo model port to gather required inputs, inspect/download HF weights, clone and install the official reference repo in the current environment, create a localtests README skeleton, and produce a handoff before conversion or implementation.

4.2k 2d ago A 56 tokens original Apache-2.0

add-model-02-parity

02

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use during /add-model after reference/architecture study to scaffold and later activate local FastVideo component parity tests. Emphasizes early test creation, official-reference loading, standardized FastVideo loading, and non-skip handoff gates.

4.2k 2d ago A 53 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one FastVideo-native DiT/transformer component.

4.2k 2d ago A 36 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one FastVideo-native VAE component.

4.2k 2d ago A 33 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one FastVideo-native text, image, audio, or compound encoder component.

4.2k 2d ago A 40 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one non-DiT, non-VAE, non-encoder FastVideo component.

4.2k 2d ago A 42 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use during /add-model Phase 5 to write and verify a FastVideo checkpoint conversion script after native component prototypes expose FastVideo state-dict keys/shapes.

4.2k 2d ago A 39 tokens original Apache-2.0

add-model-08-trace

08

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use during /add-model Phase 6 when component parity has failed and root cause requires layer-by-layer divergence analysis. Uses FastVideo activation trace first, falling back to custom hooks only for boundaries or stats the utility cannot observe.

4.2k 2d ago A 52 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use during /add-model Phase 7 after all required component parity tests pass to define FastVideo pipeline wiring, configs, presets, registry entries, examples, smoke tests, and pipeline parity tests.

4.2k 2d ago A 46 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Review rubric for FastVideo PRs that add or modify model families, variants, first-class components, checkpoint conversion, pipelines, parity coverage, or generated-media quality baselines. Use when reviewing a PR whose diff touches fastvideo/models/, fastvideo/pipelines/basic/, fastvideo/registry.py…

4.2k 2d ago A 104 tokens original Apache-2.0

add-model

11

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Manual /add-model workflow for implementing a FastVideo model or first-class component port after add-model-01-prep has staged reference code and weights. Organizes the port into numbered phases with conversion rules, component policies, parity gates, and handoff checks.

4.2k 2d ago A 55 tokens original Apache-2.0

ci-runner

12

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Work on FastVideo's Slurm-only, change-aware GPU CI lanes, static Buildkite graph, trusted ci-runner policy, lane scripts, and GB200 validation.

4.2k 2d ago A 38 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Decompose an oversized FastVideo pipeline PR into a stack of independently-reviewable PRs. Tiers the diff by blast radius (invisible / dead code / cross-cutting infra / activation), produces a branch graph and worktree bootstrap, drafts the AGENTS.md manifest, flags missing tests on cross-cutting infra changes, and…

4.2k 2d ago A 79 tokens original Apache-2.0

dreamverse-deploy

14

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Use when redeploying the migrated Dreamverse app backend and frontend on a chosen local GPU; tears down existing ports, launches services, and waits for readiness checks.

4.2k 2d ago A 38 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Re-seed the HF performance-tracking baseline for an intentional runtime, dependency, environment-caused benchmark shift, or reviewed v2 calibration using one or more reviewed normalized performance JSONs. Use when performance CI fails because metrics such as latency, throughput, component time, or peak memory changed…

4.2k 2d ago A 162 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Re-seed HF reference videos for a single existing SSIM test on Modal L40S. Always backs up current refs locally first, regenerates on Modal, pauses for the user to eyeball before-vs-after quality, then overwrites the targeted model subtree on FastVideo/ssim-reference-videos with --force. Use when an intentional code…

4.2k 2d ago A 130 tokens original Apache-2.0

hao-ai-lab/FastVideo

Skill Claude CodeCodex

Seed HF reference artefacts for a single newly-added SSIM test (pixel .mp4 for runtexttovideosimilaritytest-style tests, or latent .pt for runtexttolatentsimilaritytest-style tests). Runs the test on Modal L40S, downloads the generated artefacts via modal volume get, pauses for the user to verify (visual eyeball for…

4.2k 2d ago A 146 tokens original Apache-2.0

FastVideo AGENTS.md

18

hao-ai-lab/FastVideo

Instructions file CodexOpenCode

Instructions for hao-ai-lab/FastVideo, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.

4.2k 2d ago A 1,337 tokens original Apache-2.0

FastVideo CLAUDE.md

19

hao-ai-lab/FastVideo

Instructions file

Instructions for hao-ai-lab/FastVideo, a project described as: A unified inference and post-training framework for accelerated video generation.

4.2k 2d ago A 5 tokens copy · 100% Apache-2.0