diffusers/pr_12652/en/api/models/glm_image_transformer2d.md

GlmImageTransformer2DModel

A Diffusion Transformer model for 2D data from [GlmImageTransformer2DModel] (TODO).

GlmImageTransformer2DModel[[diffusers.GlmImageTransformer2DModel]]

diffusers.GlmImageTransformer2DModel[[diffusers.GlmImageTransformer2DModel]]

Source

Parameters:

patch_size (int, defaults to 2) : The size of the patches to use in the patch embedding layer.

in_channels (int, defaults to 16) : The number of channels in the input.

num_layers (int, defaults to 30) : The number of layers of Transformer blocks to use.

attention_head_dim (int, defaults to 40) : The number of channels in each head.

num_attention_heads (int, defaults to 64) : The number of heads to use for multi-head attention.

out_channels (int, defaults to 16) : The number of channels in the output.

text_embed_dim (int, defaults to 1472) : Input dimension of text embeddings from the text encoder.

time_embed_dim (int, defaults to 512) : Output dimension of timestep embeddings.

condition_dim (int, defaults to 256) : The embedding dimension of the input SDXL-style resolution conditions (original_size, target_size, crop_coords).

pos_embed_max_size (int, defaults to 128) : The maximum resolution of the positional embeddings, from which slices of shape H x W are taken and added to input patched latents, where H and W are the latent height and width respectively. A value of 128 means that the maximum supported height and width for image generation is 128 * vae_scale_factor * patch_size => 128 * 8 * 2 => 2048.

sample_size (int, defaults to 128) : The base resolution of input latents. If height/width is not provided during generation, this value is used to determine the resolution as sample_size * vae_scale_factor => 128 * 8 => 1024