Comfy-Org/ComfyUI · error · ValueError

The Uni3C ControlNet only works with Wan models.

Error message

The Uni3C ControlNet only works with Wan models.

What it means

After confirming a Uni3C ControlNet, the node reads the diffusion model's dim attribute to match dimensions. Wan DiT models expose dim; models without a dim attribute (getattr returns None) are by definition not Wan-family, so the node refuses to patch them.

Source

Thrown at comfy_extras/nodes_model_patch.py:731

                              "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:
    def __init__(self, model_patch, encoded_image):
        self.model_patch = model_patch
        self.encoded_image = encoded_image

View on GitHub (pinned to 1c6d8d45b3)

Solutions

1. Use a Wan-family video model as the model input (e.g. Wan 2.1/2.2 DiT checkpoints loaded through the Wan loader).
2. If using a custom Wan-derived architecture, expose a dim attribute on diffusion_model or patch via a custom node.
3. Double-check the checkpoint loader pointed at a Wan model file.

model_dim = getattr(model.get_model_object('diffusion_model'), 'dim', None)
if model_dim is None:
    raise UserFacingError('Uni3C requires a Wan-family model')

def is_wan_model(model) -> bool:
    return getattr(model.get_model_object('diffusion_model'), 'dim', None) is not None

When it happens

Trigger: Connecting a non-Wan diffusion model (Flux, SD3, Hunyuan, etc.) to the model input; the check is 'getattr(diffusion_model, "dim", None) is None'.

Common situations: Reusing a Flux/SD workflow and swapping only the controlnet branch; loading a Wan-adjacent custom model that does not expose the standard dim attribute.

Related errors

• The connected model patch is not a Uni3C ControlNet.
• y is None, did you try using a controlnet for SDXL on SD1?
• The number of controls is not equal to the number of skip co
• This Uni3C ControlNet expects a Wan model with dim {}, the l
• Control type {max_type_name}({max_type}) is out of range for

AI-assisted analysis of Comfy-Org/ComfyUI@1c6d8d45b3 (2026-08-14). Data as JSON: /api/errors/6a63e678af0086d6. Report an issue: GitHub.