mudler/LocalAI · error · ValueError

Unknown pipeline class '{class_name}'. Available pipelines:

Error message

Unknown pipeline class '{class_name}'. Available pipelines: {', '.join(sorted(registry.keys())[:20])}...

What it means

Raised by resolve_pipeline_class when class_name was provided but neither an exact nor case-insensitive match exists in the pipeline registry. The message lists up to 20 sorted registry keys to guide correction.

Source

Thrown at backend/python/diffusers/diffusers_dynamic_loader.py:348

    Returns:
        The resolved pipeline class.

    Raises:
        ValueError: If no pipeline could be resolved.
    """
    registry = get_pipeline_registry()
    aliases = get_task_aliases()

    # 1. Direct class name lookup
    if class_name:
        if class_name in registry:
            return registry[class_name]
        # Try case-insensitive match
        for name, cls in registry.items():
            if name.lower() == class_name.lower():
                return cls
        raise ValueError(
            f"Unknown pipeline class '{class_name}'. "
            f"Available pipelines: {', '.join(sorted(registry.keys())[:20])}..."
        )

    # 2. Task alias lookup
    if task:
        task_lower = task.lower().replace('_', '-')
        if task_lower in aliases:
            # Return the first matching pipeline for this task
            matching_classes = aliases[task_lower]
            if matching_classes:
                return registry[matching_classes[0]]

        # Try partial matching
        for alias, classes in aliases.items():
            if task_lower in alias or alias in task_lower:
                if classes:
                    return registry[classes[0]]

View on GitHub (pinned to 44413a9d06)

Solutions

Use the exact diffusers class name (e.g. 'StableDiffusionXLPipeline'); the match is case-insensitive but punctuation-sensitive.
If you meant a task, pass it via the task= argument instead of class_name (task aliases are handled separately).
Compare against the 'Available pipelines' list in the error message and correct spelling.
Upgrade diffusers if the class genuinely should exist.

Example fix

# before
load_diffusers_pipeline(class_name="stable-diffusion-xl")

# after
load_diffusers_pipeline(class_name="StableDiffusionXLPipeline")

Defensive patterns

Strategy: validation

Validate before calling

registry = get_pipeline_registry()
name_map = {k.lower(): k for k in registry}
canonical = name_map.get(class_name.lower())
assert canonical, f"unknown pipeline {class_name!r}"

Type guard

def is_known_pipeline(class_name: str) -> bool:
    lowered = {k.lower() for k in get_pipeline_registry()}
    return class_name.lower() in lowered

Try / catch

try:
    cls = resolve_pipeline_class(class_name=name, ...)
except ValueError as e:
    # error message lists valid names; re-surface to the API consumer
    return error_reply(str(e))

Prevention

Feed class names from a dropdown built off get_available_pipelines(), not free text.
Use exact diffusers class spellings (CamelCase ending in 'Pipeline').
Validate once at config load rather than at generation time.

When it happens

Trigger: Calling load_diffusers_pipeline / resolve_pipeline_class with a class_name like 'StableDiffusionXL' (truncated), 'stable-diffusion-xl-pipeline' (slug form), or a class unknown to the installed diffusers.

Common situations: Users passing model repo slugs or task names in the class_name field, casing mismatches beyond the case-insensitive fallback (e.g. hyphens/underscores), or a pipeline class from a newer diffusers than installed.

Related errors

AI-assisted analysis of mudler/LocalAI@44413a9d06 (2026-08-15). Data as JSON: /api/errors/1e6c49593aebbbe0. Report an issue: GitHub.