# HiDreamImageTransformer2DModel

Model Transformer untuk data seperti gambar dari [HiDream-I1](https://huggingface.co/HiDream-ai).

Model dapat dimuat dengan potongan kode berikut.

```python
from diffusers import HiDreamImageTransformer2DModel

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

## Memuat checkpoint kuantisasi GGUF untuk HiDream-I1

Checkpoint GGUF untuk `HiDreamImageTransformer2DModel` dapat dimuat menggunakan `~FromOriginalModelMixin.from_single_file`

```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)
```

[Sumber](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)
```

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

**Parameter:**

hidden_states (`torch.Tensor` dengan bentuk `(batch_size, in_channels, height, width)` atau `(batch_size, patch_height * patch_width, patch_size * patch_size * channels)`) : `hidden_states` masukan.

timesteps (`torch.LongTensor`) : Digunakan untuk menunjukkan langkah denoising.

encoder_hidden_states_t5 (`torch.Tensor`) : Embedding kondisional yang dihitung dari pengkode teks T5.

encoder_hidden_states_llama3 (`torch.Tensor`) : Embedding kondisional yang dihitung dari encoder teks Llama3.

pooled_embeds (`torch.Tensor`) : Embedding teks yang telah dipooling, digunakan untuk kondisioning tambahan.

img_ids (`torch.Tensor`, *opsional*) : ID posisi gambar untuk hidden states yang di-patch.

img_sizes (`list` dari `tuple` dari `int`, *opsional*) : Ukuran grid patch per sampel yang digunakan untuk unpatchify output.

hidden_states_masks (`torch.Tensor`, *opsional*) : Mask di atas `hidden_states` yang telah di-patch.

attention_kwargs (`dict`, *opsional*) : Kamus kwargs yang jika ditentukan akan diteruskan ke `AttentionProcessor` seperti yang didefinisikan di bawah `self.processor` dalam [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).

return_dict (`bool`, *opsional*, defaultnya `True`) : Apakah akan mengembalikan `~models.transformer_2d.Transformer2DModelOutput` alih-alih tuple biasa.

**Mengembalikan:**

Jika `return_dict` bernilai True, sebuah `~models.transformer_2d.Transformer2DModelOutput` akan dikembalikan, selain itu sebuah `tuple` di mana elemen pertama adalah tensor sampel.

Metode forward dari [HiDreamImageTransformer2DModel](/docs/diffusers/v0.43.0/id/api/models/hidream_image_transformer#diffusers.HiDreamImageTransformer2DModel).

## 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)
```

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

**Parameter:**

sample (`torch.Tensor` dengan bentuk `(batch_size, num_channels, height, width)` atau `(batch size, num_vector_embeds - 1, num_latent_pixels)` jika [Transformer2DModel](/docs/diffusers/v0.43.0/id/api/models/transformer2d#diffusers.Transformer2DModel) bersifat diskrit) : Output hidden states yang dikondisikan pada input `encoder_hidden_states`. Jika diskrit, mengembalikan distribusi probabilitas untuk piksel laten yang tidak berisik.

Output dari [Transformer2DModel](/docs/diffusers/v0.43.0/id/api/models/transformer2d#diffusers.Transformer2DModel).