diffusers/pr_13881/en/api/models/flux_transformer.md

FluxTransformer2DModel

A Transformer model for image-like data from Flux.

FluxTransformer2DModel[[diffusers.FluxTransformer2DModel]]

• patch_size (int, defaults to 1) -- Patch size to turn the input data into small patches.
• in_channels (int, defaults to 64) -- The number of channels in the input.
• out_channels (int, optional, defaults to None) -- The number of channels in the output. If not specified, it defaults to in_channels.
• num_layers (int, defaults to 19) -- The number of layers of dual stream DiT blocks to use.
• num_single_layers (int, defaults to 38) -- The number of layers of single stream DiT blocks to use.
• attention_head_dim (int, defaults to 128) -- The number of dimensions to use for each attention head.
• num_attention_heads (int, defaults to 24) -- The number of attention heads to use.
• joint_attention_dim (int, defaults to 4096) -- The number of dimensions to use for the joint attention (embedding/channel dimension of encoder_hidden_states).
• pooled_projection_dim (int, defaults to 768) -- The number of dimensions to use for the pooled projection.
• guidance_embeds (bool, defaults to False) -- Whether to use guidance embeddings for guidance-distilled variant of the model.
• axes_dims_rope (tuple[int], defaults to (16, 56, 56)) -- The dimensions to use for the rotary positional embeddings.

The Transformer model introduced in Flux.

Reference: https://blackforestlabs.ai/announcing-black-forest-labs/

• hidden_states (torch.Tensor of shape (batch_size, image_sequence_length, in_channels)) -- Input hidden_states.
• encoder_hidden_states (torch.Tensor of shape (batch_size, text_sequence_length, joint_attention_dim)) -- Conditional embeddings (embeddings computed from the input conditions such as prompts) to use.
• pooled_projections (torch.Tensor of shape (batch_size, projection_dim)) -- Embeddings projected from the embeddings of input conditions.
• timestep ( torch.LongTensor) -- Used to indicate denoising step.
• img_ids (torch.Tensor) -- Image position ids used to compute the rotary positional embeddings.
• txt_ids (torch.Tensor) -- Text position ids used to compute the rotary positional embeddings.
• guidance (torch.Tensor, optional) -- Guidance scale embedding used for guidance-distilled variants of the model.
• controlnet_block_samples (list of torch.Tensor, optional) -- A list of tensors that if specified are added to the residuals of transformer blocks.
• controlnet_single_block_samples (list of torch.Tensor, optional) -- A list of tensors that if specified are added to the residuals of single transformer blocks.
• controlnet_blocks_repeat (bool, optional, defaults to False) -- Whether to repeat the controlnet block samples across all transformer blocks.
• joint_attention_kwargs (dict, optional) -- A kwargs dictionary that if specified is passed along to the AttentionProcessor as defined under self.processor in diffusers.models.attention_processor.
• return_dict (bool, optional, defaults to True) -- Whether or not to return a ~models.transformer_2d.Transformer2DModelOutput instead of a plain tuple.If return_dict is True, an ~models.transformer_2d.Transformer2DModelOutput is returned, otherwise a tuple where the first element is the sample tensor.

The FluxTransformer2DModel forward method.