mirror of
https://github.com/Haidra-Org/AI-Horde.git
synced 2026-11-06 05:17:31 +00:00
tazlin
20c4f08065
- model_reference.py loads image_generation through horde_model_reference's ModelReferenceManager (REPLICA, GitHub fallback) with the PRIMARY's pending queue overlaid via PendingModelProvider, so beta models are known models; HORDE_BETA_MODEL_CATEGORIES and HORDE_BETA_MODELS_API_KEY control the overlay, the raw GitHub URL overrides and the expired zmodel branch gate are gone, and stable_diffusion_names is every record rather than a hard-coded baseline allowlist. - Baselines are the horde_model_reference enum spelling end to end; get_model_baseline returns a record's baseline verbatim (unknown strings pass through) with the customizer name-suffix fallbacks, get_all_model_baselines shares them. - baseline_policy.py: baseline_violation composes the request rules from two authorities, the served baseline record (weights and mechanisms that exist: remix, transparent, qr_code, unavailable control types, flow matching) and bridge_supports (which bridge releases render hires_fix, control_type, flow_shift, transparent); a feature no known worker kind renders is refused with the existing return codes. policy() reads kudos, batching, TTL and resolution floor from the record with par defaults, replacing the duplicated kudos ladders, BASELINE_BATCHING_MULTIPLIERS, FLOW_SHIFT_BASELINES and the per-baseline branches in validation.py, stable.py, worker.py, waiting_prompt.py and processing_generation.py. - ImageAsyncGenerate.validate validates against the effective model list, which a style may have substituted; get_highest_model_batching_multiplier resolves baselines instead of looking model names up in a baseline-keyed dict; the dry-run quote applies the same qr_code and hires factors the charge does; resolution floors cover every large architecture. - The KnownImageModel mirror takes ImageGenerationModelRecord objects; the manager's baseline store is refreshed on the hourly reference refresh. - Tests seed the reference with real records (model_reference_seed.py); docs for the loader, the policy table and adding a baseline.
1.3 KiB
1.3 KiB
Reference
How the running service behaves, down to the classes, caches, and gate orderings involved. These pages are for reading alongside the code.
The concepts they assume (what a worker is, what a job's lifecycle means) are in
haidra-assets/docs.
Documents
| Document | Summary |
|---|---|
| Kudos accounting reference | The mutation and consumption contract: accounting events, projection targets, reservations, the lock order, and the read models. |
| Samplers and schedulers reference | What sampler_name and scheduler select, why deterministic samplers agree once converged, measured steps-to-converge and cost, and the combinations known to fail. |
| Image baseline policy reference | The two authorities a baseline-dependent request is checked against, what each one decides, and what applies to a baseline with no record. |
| Image model reference loader reference | Where the image model reference comes from, how beta (pending) models are merged over it, the environment that configures both, and what the loader exposes. |