models
34 memberslucid.modelsLucid 3.0 model zoo — public surface.
Model Families
Vision Models
46 familieslucid.models.visionVision model families — chronological order of publication.
Text Models
5 familieslucid.models.textText model families — Phase 4 of the model zoo.
Generative Models
20 familieslucid.models.generativeImage-generative model families — Phase 5 of the model zoo.
Multimodal Models
1 familieslucid.models.multimodalModels whose input spans more than one modality.
Classes
AutoConfig2 methodsGeneric config loader — return the ModelConfig for any name.
AutoModelAuto-dispatching wrapper that loads the backbone of any family.
AutoModelForImageClassificationAuto-dispatching wrapper that loads a registered image classifier.
AutoModelForImageGenerationAuto-dispatching wrapper that loads an image-generation model.
AutoModelForLanguageModelingAuto-dispatching wrapper that loads a language model.
AutoModelForObjectDetectionAuto-dispatching wrapper that loads a registered object detector.
AutoModelForSemanticSegmentationAuto-dispatching wrapper that loads a semantic-segmentation model.
AutoModelForSequenceClassificationAuto-dispatching wrapper that loads a sentence-level classifier.
AutoModelForTokenClassificationAuto-dispatching wrapper that loads a per-token classifier.
AutoModelForWorldModelingAuto-dispatching wrapper that loads a world model.
ModelConfig4 methodsBase class for every model's configuration dataclass.
PretrainedModel6 methodsBase for every Lucid model that supports the pretrained-checkpoint flow.
ModelOutput7 methodsBase for all model-forward output dataclasses.
BaseModelOutput1 methodsGeneric backbone forward output — sequence model variant.
BaseModelOutputWithPooling1 methodsBackbone output + pooled representation (e.g. CLS).
ImageClassificationOutput1 methodsOutput of any {Family}ForImageClassification model.
ObjectDetectionOutput1 methodsOutput of any {Family}ForObjectDetection model.
InstanceSegmentationOutput1 methodsOutput of any instance-segmentation model.
SemanticSegmentationOutput1 methodsOutput of any {Family}ForSemanticSegmentation model.
CausalLMOutput1 methodsOutput of any causal (left-to-right) language model head.
MaskedLMOutput1 methodsOutput of any masked-LM head (BERT, RoFormer, …).
Seq2SeqLMOutput1 methodsOutput of any encoder-decoder seq2seq language model.
SequenceClassificationOutput1 methodsOutput of any whole-sequence classification head.
TokenClassificationOutput1 methodsOutput of any per-token classification head (NER, POS, chunking).
QuestionAnsweringOutput1 methodsOutput of any extractive span-prediction head.
DiffusionModelOutput1 methodsSingle-step output of a diffusion U-Net's forward pass.
VAEOutput1 methodsEnd-to-end VAE forward output.
NormalizingFlowOutput1 methodsForward output of an exact-likelihood normalizing flow.
GenerationOutput1 methodsFinal result of a generative model's sampling loop.
Functions
create_model→ PretrainedModelLook up name and call its factory — the timm-style entry point.
is_model→ boolReturn whether name is registered (case / separator insensitive).
list_models→ list[str]List all registered model names, optionally filtered by task / family.
model_entrypoint→ ModelFactoryReturn the registered factory callable for name.
register_model→ Callable[[ModelFactory], ModelFactory]Decorator that registers a factory function under its __name__.