These ports were marked pending removal in #1820. Each has a newer, maintained counterpart in the repo, and their model-specific hooks leaked into shared stages, request fields, CLI args, and loaders. Remove each model's code, configs, presets, examples, converters, tests, cookbook pages, CI planner rules, and registry entries, along with the shared-code hooks only they used: - camera kwargs (GameCraft camera_states, DreamX y_camera) in the shared denoising loop - LongCat refine branches in latent preparation, the decoding crop, the --bsa-* CLI args, its train model, and third_party/longcat_video - Z-Image cfg_normalization/cfg_truncation and GameCraft/DreamX camera/action fields in SamplingParam, ForwardBatch, and the schema - the GLM-Image vision-language loader and the TurboDiffusion rCM scheduler and SLA auto-select in the train entrypoint - the Wan definition groups that only preserved DreamX detector order Removed env vars and their legacy aliases move to DEPRECATED_VARIABLES per the env-var policy. Matrix Game 2.0 stays: the new trainer's world model scenarios depend on it. The SLA and BSA attention backends stay. The TurboDiffusion int8 kernels in fastvideo-kernel are left for a separate kernel PR. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Inference Configs
These files are nested inference configs for the config-first CLI.
Run them with:
fastvideo generate --config scripts/inference/<config>.yaml
Or use the helper wrapper:
bash scripts/inference/run.sh scripts/inference/<config>.yaml
Override config values with dotted paths:
fastvideo generate --config scripts/inference/<config>.yaml \
--request.sampling.seed 42 \
--request.prompt "A panda skiing at sunset"
The same overrides work through the wrapper:
bash scripts/inference/run.sh scripts/inference/<config>.yaml \
--generator.engine.num_gpus 2 \
--request.output.output_path outputs/custom_run
Some configs require an attention backend environment variable. When needed, the file header shows the exact command to use.