Menu
Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one FastVideo-native VAE component.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
| name | add-model-04-port-vae |
| description | Use during /add-model Phase 4 or Phase 6 to prototype or parity-debug one FastVideo-native VAE component. |
Prototype or parity-debug one VAE or autoencoder in FastVideo-native code. This skill covers video, image, and audio VAEs.
Follow ../add-model/shared/component_skill_common.md and require the complete
packet from ../add-model/contracts/component_context.md.
VAE-specific packet fields:
component: VAE or autoencoder name.parity_test: tests/local_tests/vaes/test_<family>_<component>_parity.py.weights: converted VAE dir, HF subfolder, or local official path.target_files: fastvideo/models/vaes/<arch_or_family>.py and
fastvideo/configs/models/vaes/<arch_or_family>.py.Use the common prototype and parity-debug modes from
../add-model/shared/component_skill_common.md.
VAE-specific prototype concerns include latent normalization, stochastic posterior behavior, tiling incompatibility, temporal/spatial/audio layout, and decode output containers.
Apply the shared reuse proof. VAE-specific comparison must include latent layout, temporal/spatial/audio compression, scaling factor, mean/std normalization, posterior behavior, encode/decode output objects, tiling flags, and cropping.
fastvideo/models/vaes/common.py::ParallelTiledVAE.VAEConfig and VAEArchConfig in
fastvideo/configs/models/vaes/base.py.fastvideo/configs/models/vaes/__init__.py.EntryClass = <ClassName> in the model file._class_name through ModelRegistry and
load converted component weights from the VAE subdir.oobleck.py, autoencoder_kl.py, wanvae.py,
ltx2vae.py, and gamecraftvae.py.fastvideo/layers/AGENTS.md.oobleck.py,
autoencoder_kl.py); name family-specific VAEs by family.VAEArchConfig; put load_encoder,
load_decoder, tiling, dtype, and pretrained path fields on VAEConfig.../add-model/shared/common_rules.md.Follow the shared prototype success criteria.
Run the shared parity-debug loop. The component test command is:
pytest <parity_test> -v -s
For numerical drift, check normalization, latent scaling, posterior mode vs sample, channel order, and temporal/spatial/audio cropping before changing layers.
Follow ../add-model/shared/common_rules.md and the component-specific guidance
in ../add-model/shared/component_skill_common.md. VAE-specific ask cases include
dropping an encode/decode path, accepting an unsupported private op, or choosing
between incompatible official VAE definitions.
Return ../add-model/contracts/component_skill_handoff.md following the common
handoff rules in ../add-model/shared/component_skill_common.md.
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 for an accepted reason and the rolling median baseline in FastVideo/performance-tracking must be advanced, or when a new v2 exact comparable identity needs its first approved baseline. The workflow backs up existing history under /tmp, validates all source JSONs for the same legacy (model_id, gpu_type) target or the same v2 exact identity, rejects internally inconsistent source batches, uploads one success=true baseline record per accepted source JSON, and offers to clean local temp state after a successful upload.
Seed HF reference artefacts for a single newly-added SSIM test (pixel `.mp4` for `run_text_to_video_similarity_test`-style tests, or latent `.pt` for `run_text_to_latent_similarity_test`-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 mp4, numerics dump for pt), then uploads only that test's files to `FastVideo/ssim-reference-videos`. Use when a new `fastvideo/tests/ssim/test_*_similarity.py` has just been added and has no references on HF yet.
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.
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 extracts lessons from the PR body.
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.
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.