lars
4b2e0ba98e
CI / Format (ruff format) (push) Successful in 33s
CI / Lint (ruff check) (push) Successful in 36s
CI / Sync project version with tag (push) Has been skipped
CI / Type check (ty) (push) Successful in 27s
CI / Lint (ruff check) (pull_request) Successful in 27s
CI / Format (ruff format) (pull_request) Successful in 29s
CI / Tests (push) Successful in 3m33s
CI / Sync project version with tag (pull_request) Has been skipped
CI / Bump version, tag, and update changelog on merge to master (push) Has been skipped
CI / Type check (ty) (pull_request) Successful in 32s
CI / Tests (pull_request) Successful in 2m45s
CI / Bump version, tag, and update changelog on merge to master (pull_request) Has been skipped
CriticModel was the one stage-shaped class left out of the trunk-registry (gitea #33), block-conditioning-registry (gitea #34), and StageModel-base (gitea #39) refactors: it hand-rolled a plain ResBlock stack, so a routed/FiLM/AdaLN trunk was available to every generative stage model except the critic competing against them under WGAN-GP. CriticModel now subclasses StageModel (reusing its cond_enc construction, and a stage-2 context-fusion helper factored out of Stage2OneShot onto the base) and builds its body via build_trunk (output width 1) instead of a bespoke ResBlock loop, so trunk.type/trunk.block_conditioning now affect the critic too. Each stage's critic inherits its own generator's trunk config rather than a new critic_trunk config key, mirroring the existing critic_hidden_dim/critic_n_res_blocks "0 = inherit from generator" pattern. Router mixing (MoE) for the critic stays out of scope. Since CriticModel is training-only and never persisted for inference, and WGAN-GP is still unbenchmarked, its state_dict shape has no back-compat burden. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>