Comfy-Org/ComfyUI · error · ValueError

The connected model patch is not a Uni3C ControlNet.

Error message

The connected model patch is not a Uni3C ControlNet.

What it means

The Uni3C ControlNet apply node requires the model_patch input to actually contain a comfy.ldm.wan.uni3c.WanUni3CControlnet instance. Any other loaded ControlNet/patch model type is rejected with isinstance before its controlnet_blocks are dereferenced.

Source

Thrown at comfy_extras/nodes_model_patch.py:727

    @classmethod
    def INPUT_TYPES(s):
        return {"required": { "model": ("MODEL",),
                              "model_patch": ("MODEL_PATCH",),
                              "vae": ("VAE",),
                              "render_video": ("IMAGE", {"tooltip": "The guidance video rendered from the camera trajectory, most commonly warped point cloud renders of the input image."}),
                              "strength": ("FLOAT", {"default": 1.0, "min": -10.0, "max": 10.0, "step": 0.01}),
                              "start_percent": ("FLOAT", {"default": 0.0, "min": 0.0, "max": 1.0, "step": 0.001}),
                              "end_percent": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 1.0, "step": 0.001}),
                              }}
    RETURN_TYPES = ("MODEL",)
    FUNCTION = "apply_patch"
    EXPERIMENTAL = True

    CATEGORY = "model/patch/wan"

    def apply_patch(self, model, model_patch, vae, render_video, strength, start_percent, end_percent):
        if not isinstance(model_patch.model, comfy.ldm.wan.uni3c.WanUni3CControlnet):
            raise ValueError("The connected model patch is not a Uni3C ControlNet.")
        cnet_dim = model_patch.model.controlnet_blocks[0].norm1.linear.in_features
        model_dim = getattr(model.get_model_object("diffusion_model"), "dim", None)
        if model_dim is None:
            raise ValueError("The Uni3C ControlNet only works with Wan models.")
        if model_dim != cnet_dim:
            raise ValueError("This Uni3C ControlNet expects a Wan model with dim {}, the loaded model has dim {}.".format(cnet_dim, model_dim))

        model_patched = model.clone()
        model_sampling = model.get_model_object("model_sampling")
        sigma_start = model_sampling.percent_to_sigma(start_percent)
        sigma_end = model_sampling.percent_to_sigma(end_percent)
        latent_format = model.get_model_object("latent_format")
        patch = WanUni3CCnetPatch(model_patch, render_video[:, :, :, :3], vae, latent_format, strength, sigma_start, sigma_end)
        model_patched.set_model_double_block_patch(patch)
        return (model_patched,)


class UsoStyleProjectorPatch:

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Load the Uni3C ControlNet with the loader node intended for it so model_patch.model is a WanUni3CControlnet.
2. Verify in Python: isinstance(model_patch.model, comfy.ldm.wan.uni3c.WanUni3CControlnet).
3. If you meant to use a different controlnet, use the generic 'Apply ControlNet' node instead of this Uni3C-specific one.

import comfy.ldm.wan.uni3c as uni3c
if not isinstance(model_patch.model, uni3c.WanUni3CControlnet):
    raise UserFacingError('load the Uni3C controlnet with its dedicated loader')

def is_uni3c_patch(model_patch) -> bool:
    import comfy.ldm.wan.uni3c as uni3c
    return isinstance(model_patch.model, uni3c.WanUni3CControlnet)

When it happens

Trigger: Loading a non-Uni3C ControlNet (standard Wan controlnet, T2I adapter, IP-adapter, etc.) through the patch loader and connecting it to this node's model_patch input.

Common situations: Reusing an existing controlnet-loading workflow where the loader is generic; selecting the wrong checkpoint from a folder of mixed control nets; a loader node that returns a wrapped/different patch class.

Related errors

• The Uni3C ControlNet only works with Wan models.
• This Uni3C ControlNet expects a Wan model with dim {}, the l
• Control type {max_type_name}({max_type}) is out of range for
• y is None, did you try using a controlnet for SDXL on SD1?
• This Controlnet needs a VAE but none was provided, please us

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/e7ed5c024d6d9826. Report an issue: GitHub.