invoke-ai/InvokeAI · error · ValueError

{self.__class__} has the config param `addition_embed_type`

Error message

{self.__class__} has the config param `addition_embed_type` set to 'image' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`

What it means

The UNet config sets `addition_embed_type='image'` (Kandinsky 2.2 style), so forward requires `added_cond_kwargs['image_embeds']` to compute the augmentation embedding from image embeddings alone. It raises when the key is missing from `added_cond_kwargs`.

Source

Thrown at invokeai/backend/hidiffusion/hidiffusion.py:1105

                if "text_embeds" not in added_cond_kwargs:
                    raise ValueError(
                        f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `text_embeds` to be passed in `added_cond_kwargs`"
                    )
                text_embeds = added_cond_kwargs.get("text_embeds")
                if "time_ids" not in added_cond_kwargs:
                    raise ValueError(
                        f"{self.__class__} has the config param `addition_embed_type` set to 'text_time' which requires the keyword argument `time_ids` to be passed in `added_cond_kwargs`"
                    )
                time_ids = added_cond_kwargs.get("time_ids")
                time_embeds = self.add_time_proj(time_ids.flatten())
                time_embeds = time_embeds.reshape((text_embeds.shape[0], -1))
                add_embeds = torch.concat([text_embeds, time_embeds], dim=-1)
                add_embeds = add_embeds.to(emb.dtype)
                aug_emb = self.add_embedding(add_embeds)
            elif self.config.addition_embed_type == "image":
                # Kandinsky 2.2 - style
                if "image_embeds" not in added_cond_kwargs:
                    raise ValueError(
                        f"{self.__class__} has the config param `addition_embed_type` set to 'image' which requires the keyword argument `image_embeds` to be passed in `added_cond_kwargs`"
                    )
                image_embs = added_cond_kwargs.get("image_embeds")
                aug_emb = self.add_embedding(image_embs)
            elif self.config.addition_embed_type == "image_hint":
                # Kandinsky 2.2 - style
                if "image_embeds" not in added_cond_kwargs or "hint" not in added_cond_kwargs:
                    raise ValueError(
                        f"{self.__class__} has the config param `addition_embed_type` set to 'image_hint' which requires the keyword arguments `image_embeds` and `hint` to be passed in `added_cond_kwargs`"
                    )
                image_embs = added_cond_kwargs.get("image_embeds")
                hint = added_cond_kwargs.get("hint")
                aug_emb, hint = self.add_embedding(image_embs, hint)
                sample = torch.cat([sample, hint], dim=1)

            emb = emb + aug_emb if aug_emb is not None else emb

            if self.time_embed_act is not None:

View on GitHub (pinned to 0b6a024f2f)

Solutions

1. Pass `added_cond_kwargs={'image_embeds': image_embeds}` (from Kandinsky's image encoder / CLIP vision model) to forward
2. Confirm the checkpoint type: Kandinsky 2.2 uses only image embeds; 2.1 needs text+image
3. Reload a non-image-conditioned UNet if image conditioning is not intended

Example fix

// before
noise_pred = unet(sample, t, encoder_hidden_states=text_emb)
// after
noise_pred = unet(sample, t, encoder_hidden_states=text_emb,
                  added_cond_kwargs={'image_embeds': image_embeds})

if getattr(unet.config, 'addition_embed_type', None) == 'image' and not (added_cond_kwargs and 'image_embeds' in added_cond_kwargs):
    raise ValueError("image-embedding UNet requires added_cond_kwargs={'image_embeds': ...}")

def has_image_embeds(added_cond_kwargs) -> bool:
    return isinstance(added_cond_kwargs, dict) and 'image_embeds' in added_cond_kwargs

try:
    out = unet(sample, t, emb, added_cond_kwargs=ackw)
except ValueError as e:
    if 'image_embeds' in str(e):
        ackw = {'image_embeds': image_embeds}; out = unet(sample, t, emb, added_cond_kwargs=ackw)
    else: raise

When it happens

Trigger: Calling forward on a UNet with `config.addition_embed_type == 'image'` (Kandinsky 2.2) without `added_cond_kwargs={'image_embeds': ...}`.

Common situations: Loading a Kandinsky 2.2 UNet and calling it with a generic SD-style signature; migrating pipelines between Kandinsky 2.1 (text_image) and 2.2 (image) where the required kwargs differ; omitting `added_cond_kwargs` entirely in custom loops.

Understand the failure class

Background: "missing required argument" and "the following required arguments were not provided": what required-argument errors mean and how to fix them — this error's family across 20 libraries.

Related errors

• {self.__class__} has the config param `addition_embed_type`
• {self.__class__} has the config param `encoder_hid_dim_type`
• class_labels should be provided when num_class_embeds > 0
• {self.__class__} has the config param `addition_embed_type`
• {self.__class__} has the config param `addition_embed_type`

AI-assisted analysis of invoke-ai/InvokeAI@0b6a024f2f (2026-08-29). Data as JSON: /api/errors/8578ad059cc8f312. Report an issue: GitHub.