load_transformer threads **kwargs into its from_pretrained and from_single_file branches. The native dispatch branch bypasses both loaders and builds via cls.from_config, so those kwargs were dropped there. Thread them through load, build_component, and build_component_quantized into from_config so callers passing extra args alongside native_spec are honored instead of silently dropped. Siblings do not receive them.
217-line bespoke loader collapses to a 40-line ANIMA_SPEC in
pipelines/anima/__init__.py (Cosmos converter + llm_adapter sibling +
Cosmos 1.0 forbidden marker).
Drop the class-keyed REGISTRY: Anima and raw Cosmos share
CosmosTransformer3DModel but need different specs. Specs pass via
explicit native_spec= kwarg; make_default_spec(cls) covers the
auto-converter case.
Replaces anima_lora.py's bespoke try_load_lora / group_keys /
resolve_network_key with thin wrappers binding native_loader's generics
to anima's prefix tuples and resolve_targets, mirroring flux2 / zimage /
chroma / ernie. The hand-rolled apply_lora_alphas bake-with-balance
pass goes away; alpha / scale / dora_scale flow through NetworkWeights.w
to NetworkModule.calc_scale at apply time.
native_loader gains an optional network_prefix kwarg (str or
Callable[[prefix_used], str], default "lora_transformer_") used when
constructing network_key. Anima passes a callable picking
lora_transformer_ / lora_llm_adapter_ / lora_te_ per matched prefix.
Single-component siblings keep the default and are unchanged.
network.NetworkModule.apply_weight_decompose grows a dual-path DoRA
convention detector. The pre-fix implementation only handled per-input
dora_scale (DoRA paper / kohya, shape (1, in)), silently broadcasting
per-output LyCORIS / PEFT dora_scale (shape (out, 1)) into an incoherent
element-wise rescaling. Detection is structural: (out, 1, ...) routes
to per-output; everything else (including the square-weight 1D ambiguity)
defaults to per-input for legacy compat. Pre-existing bug surfaced by
the LoKR+DoRA LyCORIS files Anima now loads.
Behavior changes:
- LoHA via the generic try_load_loha (NetworkModuleHada); covers
scenery-anima-base and any other LyCORIS .hada_w* export.
- Kohya lora_te_ prefix recognized. The legacy resolver only matched
BFL text_encoders.qwen3_06b.transformer.model. and silently dropped
lora_te_layers_N_* keys (41% of BlueArcStyle's bases were unloaded).
- LoKR+DoRA LyCORIS files now apply correctly; the per-output dora_scale
is honored instead of silently scrambled.
Adds test/test-anima-native-adapters.py: 37 offline tests across all
five prefixes (LoRA + LoHA), every COSMOS_2_FLAT_RENAME entry, DoRA
threading, marker disambiguation, try_load_chain dispatch, calc_updown
sanity, and both DoRA conventions (per-input / per-output / 1D ambiguous).
Adapter mock mirrors AnimaLLMAdapter's real module tree.
Replaces ernie's four family loaders with thin wrappers binding
native_loader's generics to ernie's prefix tuples and resolve_targets.
ErnieImageAttention has fully split to_q / to_k / to_v with no fused QKV
and ErnieImageFeedForward has three separate Linear modules, so
resolve_targets is a straight passthrough across every recognized prefix.
BARE_DIFFUSERS_PREFIXES covers layers., adaLN_modulation., final_norm.,
final_linear. for bare-diffusers exports (e.g. via save_lora_adapter).
parse_key returns (prefix_used, base, suffix) instead of the old
(network_key, suffix); parse test updated.
Replaces chroma's four family loaders with thin wrappers binding
native_loader's generics to chroma's prefix tuples and resolve_targets.
resolve_targets folds the Flux-to-diffusers rename table and the two
fused-weight splits into one path-resolution step:
- img_attn.qkv / txt_attn.qkv: ChunkSpec(idx, total=3) for equal Q/K/V
- single_blocks.linear1: ChunkSpec(start, end) for the unequal
Q/K/V/proj_mlp partition
QKV_DIMS and LINEAR1_DIMS stay as module-level constants (tests patch
them for the scaled-down mock).
Behavior changes:
- LoKR on equal-chunk QKV now dispatches to NetworkModuleLokrChunk
instead of NetworkModuleLokrSliceChunk (the slice variant was used
pre-migration for both forms since chroma had no equal-chunk path).
- LoHA on fused img_attn.qkv now binds via NetworkModuleHadaChunk
instead of being skipped; the shared HadaChunk added in the flux2 PR
is general for equal-chunks dispatch.
parse_key returns (prefix_used, base, suffix) instead of the old
(flat_key, suffix); rename happens in resolve_targets. test_static_rename_table
replaced with test_resolve_targets_static_renames driving the same
remappings through the new interface.
Replaces zimage's four family loaders with thin wrappers binding
native_loader's generics to z-image's prefix tuples and resolve_targets.
resolve_targets folds the legacy attention.qkv split and attention.out
alias rename into the path-resolution step. Fused qkv now emits three
ChunkSpec(idx, total=3) entries; attention.out / attention.out.0 /
attention.wo aliases collapse to attention.to_out.0.
BARE_DIFFUSERS_PREFIXES allows bare paths starting with layers. /
noise_refiner. / context_refiner. to pass through to the loader. This
matches real Z-Image LoRAs exported via
ZImageTransformer2DModel.save_lora_adapter().
LoHA on fused qkv now binds via NetworkModuleHadaChunk (added to shared
infra by the flux2 PR) instead of being skipped. Test renamed to
test_loha_legacy_fused_qkv_chunked.
parse_key returns (prefix_used, base, suffix) instead of the old
(network_key, suffix); parse test updated.
Covers ernie's four-family surface (LoRA, LoKR, LoHA, OFT).
ErnieImageAttention has fully split to_q / to_k / to_v with no fused QKV,
and ErnieImageFeedForward has three separate Linear modules. The loader
has no chunking, renames, or fused-target dispatch.
Mock matches diffusers.ErnieImageTransformer2DModel
(ErnieImageSharedAdaLNBlock with self_attention + mlp + RMSNorms, plus
module-level adaLN_modulation Sequential and final_linear).
Formats exercised:
- BFL / AI-toolkit
- kohya
- BFL LoKR
Covers chroma's four-family surface plus the Flux-to-diffusers rename
and the unique single-block linear1 unequal-chunk slicing.
Mock transformer matches diffusers.ChromaTransformer2DModel
(transformer_blocks with FluxAttention(added_kv_proj_dim), single
transformer_blocks with pre-only attn + proj_mlp + proj_out, plus
distilled_guidance_layer).
Formats exercised:
- BFL / AI-toolkit
- kohya
- PEFT
- LyCORIS oft_diag
install_mock_pipe patches chroma_lora.QKV_DIMS and LINEAR1_DIMS to the
test scale (HIDDEN=96, MLP_HIDDEN=384); the module otherwise hardcodes
Chroma1-HD's 3072 / 12288.
Replaces flux2's eight family loaders with thin wrappers binding
native_loader's generics to flux2's prefix tuples and resolve_targets.
Constants and helpers (has_marker, parse_key, group_by_suffixes) are
re-exported from native_loader so the offline tests address them through
flux2_lora's surface unchanged.
resolve_targets now returns (diffusers_path, ChunkSpec | None) tuples
instead of (path, idx, num_chunks). Three parse-level tests updated.
PEFT-fallback path (apply_lora_alphas, preprocess_f2_keys, apply_patch)
stays in flux2_lora.
36 tests across parsing primitives, family loaders, calc_updown shape
sanity, and the lora_apply ex_bias accumulation path. Builds a mock
Flux2-shaped transformer (HIDDEN=128, 2 double + 2 single blocks) and
writes synthesized state dicts to tempfile-managed safetensors so the
loaders' real read_state_dict path runs.
Loader fixtures include the full nine-family menu plus four prefix
variants (kohya, BFL/AI-toolkit, PEFT, bare-BFL) and the two real
ground-truth formats observed on Hugging Face: base_model.model.
(peft.save_pretrained wrapper) and lycoris_ (LyCORIS-standalone).
Generation tests cover scheduler params, color grading, and latent
corrections. Detailer tests cover model enumeration and object
detection. Both require a running SD.Next instance.
- Rename cli/api-interrogate.py to cli/api-caption.py
- Update cli/options.py, cli/process.py for new module paths
- Update cli/test-tagger.py for caption module imports
CalamitousFelicitousness
Vladimir Mandic
Zhang Hua
space-nuko
AUTOMATIC