Diffusers documentation
JoyImageEditTransformer3DModel
You are viewing main version, which requires installation from source. If you'd like
regular pip install, checkout the latest stable version (v0.42.1).
JoyImageEditTransformer3DModel
可以使用以下代码片段加载该模型。
from diffusers import JoyImageEditTransformer3DModel
transformer = JoyImageEditTransformer3DModel.from_pretrained("jdopensource/JoyAI-Image-Edit-Diffusers", subfolder="transformer", dtype=torch.bfloat16)JoyImageEditTransformer3DModel
类 diffusers.JoyImageEditTransformer3DModel
< source >( patch_size: list = [1, 2, 2]in_channels: int = 16out_channels: int | None = Nonehidden_size: int = 3072num_attention_heads: int = 24text_dim: int = 4096mlp_width_ratio: float = 4.0num_layers: int = 20rope_dim_list: list = [16, 56, 56]rope_type: str = 'rope'theta: int = 256 )
用于图像生成/编辑的 JoyImage Transformer 模型。
采用 WAN 风格条件嵌入和自定义旋转位置嵌入的双流 DiT 架构。
forward
< source >( hidden_states: Tensortimestep: Tensorencoder_hidden_states: Tensor = Nonereturn_dict: bool = True )
参数
- hidden_states（形状为
(batch_size, num_channels, num_frames, height, width)或(batch_size, num_items, num_channels, num_frames, height, width)的torch.Tensor）— 输入的hidden_states。 - timestep (
torch.LongTensor) — 用于指示去噪步骤。 - encoder_hidden_states (
torch.Tensor, 可选) — 要使用的条件嵌入（从输入条件（例如提示词）计算得出的嵌入）。 - return_dict (
bool，可选，默认为True) — 是否返回~models.transformer_2d.Transformer2DModelOutput而不是普通的元组。
Transformer2DModelOutput
类 diffusers.models.modeling_outputs.Transformer2DModelOutput
< source >( sample: torch.Tensor )
参数
- sample（形状为
(batch_size, num_channels, height, width)的torch.Tensor，或者如果 Transformer2DModel 是离散的，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。如果是离散的，则返回未加噪潜在像素的概率分布。
Transformer2DModel 的输出。