{"record":{"id":"682fcbbcaad7fe3d","repo":"invoke-ai/InvokeAI","slug":"no-diffusers-pipeline-known-for-base-config-base","errorCode":null,"errorMessage":"No diffusers pipeline known for base={config.base}, variant={config.variant}","messagePattern":"No diffusers pipeline known for base=(.+?), variant=(.+?)","errorType":"exception","errorClass":"Exception","httpStatus":null,"severity":"error","filePath":"invokeai/backend/model_manager/load/model_loaders/stable_diffusion.py","lineNumber":134,"sourceCode":"            },\n        }\n        assert isinstance(\n            config,\n            (\n                Main_Diffusers_SD1_Config,\n                Main_Diffusers_SD2_Config,\n                Main_Diffusers_SDXL_Config,\n                Main_Diffusers_SDXLRefiner_Config,\n                Main_Checkpoint_SD1_Config,\n                Main_Checkpoint_SD2_Config,\n                Main_Checkpoint_SDXL_Config,\n                Main_Checkpoint_SDXLRefiner_Config,\n            ),\n        )\n        try:\n            load_class = load_classes[config.base][config.variant]\n        except KeyError as e:\n            raise Exception(f\"No diffusers pipeline known for base={config.base}, variant={config.variant}\") from e\n\n        # Without SilenceWarnings we get log messages like this:\n        # site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n        # warnings.warn(\n        # Some weights of the model checkpoint were not used when initializing CLIPTextModel:\n        # ['text_model.embeddings.position_ids']\n        # Some weights of the model checkpoint were not used when initializing CLIPTextModelWithProjection:\n        # ['text_model.embeddings.position_ids']\n\n        with SilenceWarnings():\n            pipeline = load_class.from_single_file(config.path, torch_dtype=self._torch_dtype)\n\n        if not submodel_type:\n            return pipeline\n\n        # Proactively load the various submodels into the RAM cache so that we don't have to re-load\n        # the entire pipeline every time a new submodel is needed.\n        for subtype in SubModelType:","sourceCodeStart":116,"sourceCodeEnd":152,"githubUrl":"https://github.com/invoke-ai/InvokeAI/blob/0b6a024f2ff6a86bfb953dcdb9cc504ef7397a06/invokeai/backend/model_manager/load/model_loaders/stable_diffusion.py#L116-L152","documentation":"The single-file checkpoint loader maps (base model family, pipeline variant) pairs to diffusers from_single_file pipeline classes via a nested dict. If the combination is not in the table (e.g. an unsupported base or variant), the KeyError is caught and re-raised as this Exception. It means InvokeAI has no recipe to convert that checkpoint into a diffusers pipeline.","triggerScenarios":"Loading a single-file checkpoint whose config.base/config.variant combination has no entry in load_classes — e.g. an exotic or newer base model type, or an unusual variant, resolved at stable_diffusion.py:134.","commonSituations":"Importing checkpoints for model families not supported for single-file loading (e.g. some SD3/Flux/non-standard bases); a config record with the wrong base/variant fields; custom or community checkpoints that aren't standard SD/SDXL/SDXL-Refiner layouts.","solutions":["Use a supported base/variant: re-tag the model config with the correct BaseModelType and ModelVariantType (SD, SDXL, SDXLRefiner, etc.).","Convert the checkpoint to diffusers folder layout offline (convert_original_stable_diffusion_to_diffusers.py) and install that instead.","Upgrade InvokeAI — support for new checkpoint formats is added over time.","If the checkpoint is genuinely unsupported, load it with an external tool (ComfyUI/diffusers directly)."],"exampleFix":"// before: config records base=SD3 for a single-file checkpoint -> KeyError\n// after: correct the config or use diffusers layout\nconfig = Main_Checkpoint_Config_Base(\n    base=BaseModelType.StableDiffusionXL,\n    variant=ModelVariantType.Normal,\n    path=\"model.safetensors\",\n)","handlingStrategy":"validation","validationCode":"SUPPORTED = {(BaseModelType.StableDiffusion, ModelVariantType.Normal),\n             (BaseModelType.StableDiffusionXL, ModelVariantType.Normal),\n             (BaseModelType.StableDiffusionXL, ModelVariantType.Inpaint),\n             (BaseModelType.StableDiffusionXLRefiner, ModelVariantType.Normal)}\nif (config.base, config.variant) not in SUPPORTED:\n    raise ValueError(f\"Single-file load unsupported for {config.base}/{config.variant}\")","typeGuard":null,"tryCatchPattern":"try:\n    model = loader.load_model(config, submodel_type)\nexcept Exception as e:\n    if \"No diffusers pipeline known\" in str(e):\n        logger.error(\"Convert checkpoint to diffusers layout or fix base/variant config: %s\", e)\n    raise","preventionTips":["Set the model config's base/variant fields correctly on import.","Prefer diffusers folder layout for non-standard or newer checkpoints.","Keep InvokeAI updated for newly supported checkpoint families."],"tags":["unsupported-model","checkpoint","stable-diffusion","singlefile","variant"],"backgroundTag":"unsupported-model-architecture","analyzedSha":"0b6a024f2ff6a86bfb953dcdb9cc504ef7397a06","analyzedAt":"2026-08-29T04:46:49.967Z","schemaVersion":2},"datasetVersion":"2026-08-29T07:17:48.351Z"}