diffusers/pr_14252/en/_app/immutable/nodes/62.DI3AVeyk.js

import"../chunks/DsnmJJEf.js";import{i as x,h as E,C as I,H as l,D as f,E as D,s as M}from"../chunks/BtE7mKSK.js";import{p as w,o as y,s as e,f as z,a as c,b as L,c as g,d as u,n as h,r as p}from"../chunks/jDjavuwI.js";const R='{"title":"ErnieImageTransformer2DModel","local":"ernieimagetransformer2dmodel","sections":[{"title":"ErnieImageTransformer2DModel","local":"diffusers.ErnieImageTransformer2DModel","sections":[],"depth":2}],"depth":1}';var k=u('<meta name="hf:doc:metadata"/>'),N=u('<p></p> <!> <!> <p>A Transformer model for image-like data from <a href="https://huggingface.co/baidu/ERNIE-Image" rel="nofollow">ERNIE-Image</a>.</p> <p>A Transformer model for image-like data from <a href="https://huggingface.co/baidu/ERNIE-Image-Turbo" rel="nofollow">ERNIE-Image-Turbo</a>.</p> <!> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"><!> <p>The <a href="/docs/diffusers/pr_14252/en/api/models/ernie_image_transformer2d#diffusers.ErnieImageTransformer2DModel">ErnieImageTransformer2DModel</a> forward method.</p></div></div> <!> <p></p>',1);function A(_,b){w(b,!1),y(()=>{new URLSearchParams(window.location.search).get("fw")}),x();var a=N();E("u858l2",d=>{var m=k();M(m,"content",R),c(d,m)});var n=e(z(a),2);I(n,{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"});var o=e(n,2);l(o,{title:"ErnieImageTransformer2DModel",local:"ernieimagetransformer2dmodel",headingTag:"h1"});var t=e(o,6);l(t,{title:"ErnieImageTransformer2DModel",local:"diffusers.ErnieImageTransformer2DModel",headingTag:"h2"});var r=e(t,2),s=g(r);f(s,{name:"class diffusers.ErnieImageTransformer2DModel",anchor:"diffusers.ErnieImageTransformer2DModel",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/models/transformers/transformer_ernie_image.py#L296",parameters:[{name:"hidden_size",val:": int = 3072"},{name:"num_attention_heads",val:": int = 24"},{name:"num_layers",val:": int = 24"},{name:"ffn_hidden_size",val:": int = 8192"},{name:"in_channels",val:": int = 128"},{name:"out_channels",val:": int = 128"},{name:"patch_size",val:": int = 1"},{name:"text_in_dim",val:": int = 2560"},{name:"rope_theta",val:": int = 256"},{name:"rope_axes_dim",val:": typing.Tuple[int, int, int] = (32, 48, 48)"},{name:"eps",val:": float = 1e-06"},{name:"qk_layernorm",val:": bool = True"}]});var i=e(s,2),v=g(i);f(v,{name:"forward",anchor:"diffusers.ErnieImageTransformer2DModel.forward",source:"https://github.com/huggingface/diffusers/blob/vr_14252/src/diffusers/models/transformers/transformer_ernie_image.py#L348",parameters:[{name:"hidden_states",val:": Tensor"},{name:"timestep",val:": Tensor"},{name:"text_bth",val:": Tensor"},{name:"text_lens",val:": Tensor"},{name:"return_dict",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.ErnieImageTransformer2DModel.forward.hidden_states",description:`<strong>hidden_states</strong> (<code>torch.Tensor</code> of shape <code>(batch_size, in_channels, height, width)</code>) &#x2014;
Input <code>hidden_states</code>.`,name:"hidden_states"},{anchor:"diffusers.ErnieImageTransformer2DModel.forward.timestep",description:`<strong>timestep</strong> (<code>torch.LongTensor</code>) &#x2014;
Used to indicate denoising step.`,name:"timestep"},{anchor:"diffusers.ErnieImageTransformer2DModel.forward.text_bth",description:`<strong>text_bth</strong> (<code>torch.Tensor</code>) &#x2014;
Conditional text embeddings (embeddings computed from the input conditions such as prompts) to use,
shaped <code>(batch_size, text_length, embed_dims)</code>.`,name:"text_bth"},{anchor:"diffusers.ErnieImageTransformer2DModel.forward.text_lens",description:`<strong>text_lens</strong> (<code>torch.Tensor</code>) &#x2014;
Per-sample text sequence lengths used to build the attention mask.`,name:"text_lens"},{anchor:"diffusers.ErnieImageTransformer2DModel.forward.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether or not to return a <code>~models.transformer_2d.Transformer2DModelOutput</code> instead of a plain
tuple.`,name:"return_dict"}]}),h(2),p(i),p(r);var T=e(r,2);D(T,{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/models/ernie_image_transformer2d.md"}),h(2),c(_,a),L()}export{A as component};