diffusers/pr_14421/en/api/models/z_image_transformer2d.md

ZImageTransformer2DModel

A Transformer model for image-like data from Z-Image.

ZImageTransformer2DModel[[diffusers.ZImageTransformer2DModel]]

diffusers.ZImageTransformer2DModel[[diffusers.ZImageTransformer2DModel]]

diffusers.ZImageTransformer2DModel(all_patch_size = (2,), all_f_patch_size = (1,), in_channels = 16, dim = 3840, n_layers = 30, n_refiner_layers = 2, n_heads = 30, n_kv_heads = 30, norm_eps = 1e-05, qk_norm = True, cap_feat_dim = 2560, siglip_feat_dim = None, rope_theta = 256.0, t_scale = 1000.0, axes_dims = [32, 48, 48], axes_lens = [1024, 512, 512])

Source

forward[[diffusers.ZImageTransformer2DModel.forward]]

forward(x: list, t, cap_feats: list, return_dict: bool = True, controlnet_block_samples: dict[int, torch.Tensor] | None = None, siglip_feats: list[list[torch.Tensor]] | None = None, image_noise_mask: list[list[int]] | None = None, patch_size: int = 2, f_patch_size: int = 1)

Source

Parameters:

x (list of torch.Tensor or nested list of torch.Tensor) : Input latents. A flat list when running in standard mode, or a nested list when running in omni mode.

t (torch.Tensor) : Used to indicate denoising step.

cap_feats (list of torch.Tensor or nested list of torch.Tensor) : Conditional caption embeddings (embeddings computed from the input conditions such as prompts) to use.

return_dict (bool, optional, defaults to True) : Whether or not to return a ~models.transformer_2d.Transformer2DModelOutput instead of a plain tuple.

controlnet_block_samples (dict of int to torch.Tensor, optional) : A mapping from block index to tensor that if specified are added to the residuals of transformer blocks.

siglip_feats (list of list of torch.Tensor, optional) : Optional SigLIP image features used as additional conditioning.

image_noise_mask (list of list of int, optional) : Per-image noise masks indicating noisy vs. clean tokens in omni mode.

patch_size (int, optional, defaults to 2) : Spatial patch size used to patchify the input latents.

f_patch_size (int, optional, defaults to 1) : Temporal patch size used to patchify the input latents.

The ZImageTransformer2DModel forward method.

Flow: patchify -> t_embed -> x_embed -> x_refine -> cap_embed -> cap_refine -> [siglip_embed -> siglip_refine] -> build_unified -> main_layers -> final_layer -> unpatchify

patchify_and_embed[[diffusers.ZImageTransformer2DModel.patchify_and_embed]]

patchify_and_embed(all_image: list, all_cap_feats: list, patch_size: int, f_patch_size: int)

Source

Patchify for basic mode: single image per batch item.

patchify_and_embed_omni[[diffusers.ZImageTransformer2DModel.patchify_and_embed_omni]]

patchify_and_embed_omni(all_x: list, all_cap_feats: list, all_siglip_feats: list, patch_size: int, f_patch_size: int, images_noise_mask: list)

Source

Patchify for omni mode: multiple images per batch item with noise masks.