diffusers/pr_13966/en/api/models/stable_cascade_unet.md

StableCascadeUNet

A UNet model from the Stable Cascade pipeline.

StableCascadeUNet[[diffusers.models.StableCascadeUNet]]

• sample (torch.Tensor) -- The noisy input sample.
• timestep_ratio (torch.Tensor) -- Timestep ratio used to compute the timestep embedding.
• clip_text_pooled (torch.Tensor) -- Pooled CLIP text embeddings.
• clip_text (torch.Tensor, optional) -- Sequence-level CLIP text embeddings.
• clip_img (torch.Tensor, optional) -- CLIP image embeddings.
• effnet (torch.Tensor, optional) -- EfficientNet feature map used as additional conditioning.
• pixels (torch.Tensor, optional) -- Pixel-level conditioning tensor. If None, a tensor of zeros is used.
• sca (torch.Tensor, optional) -- Optional sca conditioning value used to build the timestep embedding.
• crp (torch.Tensor, optional) -- Optional crp conditioning value used to build the timestep embedding.
• return_dict (bool, optional, defaults to True) -- Whether or not to return a StableCascadeUNetOutput instead of a plain tuple.