# HiDreamImageTransformer2DModel

用于 [HiDream-I1](https://huggingface.co/HiDream-ai) 中类图像数据的 Transformer 模型。

可以使用以下代码片段加载该模型。

```python
from diffusers import HiDreamImageTransformer2DModel

transformer = HiDreamImageTransformer2DModel.from_pretrained("HiDream-ai/HiDream-I1-Full", subfolder="transformer", dtype=torch.bfloat16)
```

## 加载 HiDream-I1 的 GGUF 量化检查点

`HiDreamImageTransformer2DModel` 的 GGUF 检查点可以使用 `~FromOriginalModelMixin.from_single_file` 进行加载

```python
import torch
from diffusers import GGUFQuantizationConfig, HiDreamImageTransformer2DModel

ckpt_path = "https://huggingface.co/city96/HiDream-I1-Dev-gguf/blob/main/hidream-i1-dev-Q2_K.gguf"
transformer = HiDreamImageTransformer2DModel.from_single_file(
    ckpt_path,
    quantization_config=GGUFQuantizationConfig(compute_dtype=torch.bfloat16),
    dtype=torch.bfloat16
)
```

## HiDreamImageTransformer2DModel[[diffusers.HiDreamImageTransformer2DModel]]

#### diffusers.HiDreamImageTransformer2DModel[[diffusers.HiDreamImageTransformer2DModel]]

```python
diffusers.HiDreamImageTransformer2DModel(patch_size: int | None = None, in_channels: int = 64, out_channels: int | None = None, num_layers: int = 16, num_single_layers: int = 32, attention_head_dim: int = 128, num_attention_heads: int = 20, caption_channels: list[int] = None, text_emb_dim: int = 2048, num_routed_experts: int = 4, num_activated_experts: int = 2, axes_dims_rope: tuple[int, int] = (32, 32), max_resolution: tuple[int, int] = (128, 128), llama_layers: list[int] = None, force_inference_output: bool = False)
```

[源代码](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/transformers/transformer_hidream_image.py#L602)

#### forward[[diffusers.HiDreamImageTransformer2DModel.forward]]

```python
forward(hidden_states: Tensor, timesteps: LongTensor = None, encoder_hidden_states_t5: Tensor = None, encoder_hidden_states_llama3: Tensor = None, pooled_embeds: Tensor = None, img_ids: typing.Optional[torch.Tensor] = None, img_sizes: list[tuple[int, int]] | None = None, hidden_states_masks: typing.Optional[torch.Tensor] = None, attention_kwargs: dict[str, typing.Any] | None = None, return_dict: bool = True)
```

[源代码](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/transformers/transformer_hidream_image.py#L773)

**参数：**

hidden_states （形状为 `(batch_size, in_channels, height, width)` 或 `(batch_size, patch_height * patch_width, patch_size * patch_size * channels)` 的 `torch.Tensor`）：输入 `hidden_states`。

timesteps (`torch.LongTensor`)：用于指示去噪步骤。

encoder_hidden_states_t5 (`torch.Tensor`) : 由 T5 文本编码器计算得出的条件嵌入。

encoder_hidden_states_llama3 (`torch.Tensor`) : 由 Llama3 文本编码器计算得出的条件嵌入。

pooled_embeds (`torch.Tensor`) : 用于额外条件控制的池化文本嵌入。

img_ids (`torch.Tensor`, *可选*) : 用于补丁隐藏状态的图像位置 ID。

img_sizes (`list` of `tuple` of `int`, *optional*) : 用于对输出进行 unpatchify 的每个样本的 patch 网格大小。

hidden_states_masks (`torch.Tensor`, *可选*) : 应用于分块 `hidden_states` 的掩码。

attention_kwargs (`dict`, *可选*) : 一个 kwargs 字典，如果指定，将作为参数传递给 [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py) 中 `self.processor` 下定义的 `AttentionProcessor`。

return_dict (`bool`，*可选*，默认为 `True`)：是否返回 `~models.transformer_2d.Transformer2DModelOutput` 而不是普通元组。

**返回值：**

如果 `return_dict` 为 True，则返回 `~models.transformer_2d.Transformer2DModelOutput`，否则返回一个 `tuple`，其中第一个元素是样本张量。

[HiDreamImageTransformer2DModel](/docs/diffusers/v0.43.0/zh/api/models/hidream_image_transformer#diffusers.HiDreamImageTransformer2DModel) 的前向方法。

## Transformer2DModelOutput[[diffusers.models.modeling_outputs.Transformer2DModelOutput]]

#### diffusers.models.modeling_outputs.Transformer2DModelOutput[[diffusers.models.modeling_outputs.Transformer2DModelOutput]]

```python
diffusers.models.modeling_outputs.Transformer2DModelOutput(sample: torch.Tensor)
```

[源代码](https://github.com/huggingface/diffusers/blob/v0.43.0/src/diffusers/models/modeling_outputs.py#L21)

**参数：**

sample (`torch.Tensor`，形状为 `(batch_size, num_channels, height, width)`；若 [Transformer2DModel](/docs/diffusers/v0.43.0/zh/api/models/transformer2d#diffusers.Transformer2DModel) 为离散模式，则为 `(batch size, num_vector_embeds - 1, num_latent_pixels)`)：以 `encoder_hidden_states` 输入为条件的隐藏状态输出。若为离散模式，则返回未加噪潜在像素的概率分布。

[Transformer2DModel](/docs/diffusers/v0.43.0/zh/api/models/transformer2d#diffusers.Transformer2DModel) 的输出。