diffusers/pr_12249/en/_app/immutable/nodes/149.779b4949.js

import{s as _n,o as hn,n as fn}from"../chunks/scheduler.53228c21.js";import{S as yn,i as bn,e as l,s,c as d,h as wn,a as p,d as t,b as o,f as J,g as m,j as M,k as $,l as _,m as a,n as c,t as u,o as g,p as f}from"../chunks/index.100fac89.js";import{D as oe}from"../chunks/Docstring.f8721f67.js";import{C as _e}from"../chunks/CodeBlock.d30a6509.js";import{E as gn}from"../chunks/ExampleCodeBlock.24511344.js";import{H as fe,E as Mn}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.d8195636.js";function In(ie){let r,U="Examples:",b,h,y;return h=new _e({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> HunyuanImagePipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = HunyuanImagePipeline.from_pretrained(
<span class="hljs-meta">... </span>    <span class="hljs-string">&quot;hunyuanvideo-community/HunyuanImage-2.1-Diffusers&quot;</span>, torch_dtype=torch.bfloat16
<span class="hljs-meta">... </span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>prompt = <span class="hljs-string">&quot;A cat holding a sign that says hello world&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Depending on the variant being used, the pipeline call will slightly vary.</span>
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Refer to the pipeline documentation for more details.</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>image = pipe(prompt, negative_prompt=<span class="hljs-string">&quot;&quot;</span>, num_inference_steps=<span class="hljs-number">50</span>).images[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;hunyuanimage.png&quot;</span>)`,wrap:!1}}),{c(){r=l("p"),r.textContent=U,b=s(),d(h.$$.fragment)},l(i){r=p(i,"P",{"data-svelte-h":!0}),M(r)!=="svelte-kvfsh7"&&(r.textContent=U),b=o(i),m(h.$$.fragment,i)},m(i,w){a(i,r,w),a(i,b,w),c(h,i,w),y=!0},p:fn,i(i){y||(u(h.$$.fragment,i),y=!0)},o(i){g(h.$$.fragment,i),y=!1},d(i){i&&(t(r),t(b)),f(h,i)}}}function vn(ie){let r,U="Examples:",b,h,y;return h=new _e({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">import</span> torch
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> HunyuanImageRefinerPipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = HunyuanImageRefinerPipeline.from_pretrained(
<span class="hljs-meta">... </span>    <span class="hljs-string">&quot;hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers&quot;</span>, torch_dtype=torch.bfloat16
<span class="hljs-meta">... </span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>prompt = <span class="hljs-string">&quot;A cat holding a sign that says hello world&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>image = load_image(<span class="hljs-string">&quot;path/to/image.png&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Depending on the variant being used, the pipeline call will slightly vary.</span>
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Refer to the pipeline documentation for more details.</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>image = pipe(prompt, image=image, num_inference_steps=<span class="hljs-number">4</span>).images[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;hunyuanimage.png&quot;</span>)`,wrap:!1}}),{c(){r=l("p"),r.textContent=U,b=s(),d(h.$$.fragment)},l(i){r=p(i,"P",{"data-svelte-h":!0}),M(r)!=="svelte-kvfsh7"&&(r.textContent=U),b=o(i),m(h.$$.fragment,i)},m(i,w){a(i,r,w),a(i,b,w),c(h,i,w),y=!0},p:fn,i(i){y||(u(h.$$.fragment,i),y=!0)},o(i){g(h.$$.fragment,i),y=!1},d(i){i&&(t(r),t(b)),f(h,i)}}}function Tn(ie){let r,U,b,h,y,i,w,Ae="HunyuanImage-2.1 is a 17B text-to-image model that is capable of generating 2K (2048 x 2048) resolution images",ye,C,Ke="HunyuanImage-2.1 comes in the following variants:",be,G,en='<thead><tr><th align="center">model type</th> <th align="center">model id</th></tr></thead> <tbody><tr><td align="center">HunyuanImage-2.1</td> <td align="center"><a href="https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Diffusers" rel="nofollow">hunyuanvideo-community/HunyuanImage-2.1-Diffusers</a></td></tr> <tr><td align="center">HunyuanImage-2.1-Distilled</td> <td align="center"><a href="https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers" rel="nofollow">hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers</a></td></tr> <tr><td align="center">HunyuanImage-2.1-Refiner</td> <td align="center"><a href="https://huggingface.co/hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers" rel="nofollow">hunyuanvideo-community/HunyuanImage-2.1-Refiner-Diffusers</a></td></tr></tbody>',we,W,nn="<p>[!TIP][Caching](../../optimization/cache) may also speed up inference by storing and reusing intermediate outputs.</p>",Me,R,Ie,V,tn='HunyuanImage-2.1 applies <a href="https://huggingface.co/papers/2410.02416" rel="nofollow">Adaptive Projected Guidance (APG)</a> combined with Classifier-Free Guidance (CFG) in the denoising loop. <code>HunyuanImagePipeline</code> has a <code>guider</code> component (read more about <a href="../modular_diffusers/guiders">Guider</a>) and does not take a <code>guidance_scale</code> parameter at runtime. To change guider-related parameters, e.g., <code>guidance_scale</code>, you can update the <code>guider</code> configuration instead.',ve,E,Te,L,an="You can inspect the <code>guider</code> object:",Ue,N,je,q,sn="To update the guider with a different configuration, use the <code>new()</code> method. For example, to generate an image with <code>guidance_scale=5.0</code> while keeping all other default guidance parameters:",xe,z,ke,Q,He,X,on="use <code>distilled_guidance_scale</code> with the guidance-distilled checkpoint,",Je,S,$e,Y,Be,I,D,Le,re,rn="The HunyuanImage pipeline for text-to-image generation.",Ne,j,F,qe,le,ln="Function invoked when calling the pipeline for generation.",ze,B,Qe,pe,O,Pe,A,Ze,v,K,Xe,de,pn="The HunyuanImage pipeline for text-to-image generation.",Se,x,ee,Ye,me,dn="Function invoked when calling the pipeline for generation.",De,P,Fe,ce,ne,Ce,te,Ge,k,ae,Oe,ue,mn="Output class for HunyuanImage pipelines.",We,se,Re,he,Ve;return y=new fe({props:{title:"HunyuanImage2.1",local:"hunyuanimage21",headingTag:"h1"}}),R=new fe({props:{title:"HunyuanImage-2.1",local:"hunyuanimage-21",headingTag:"h2"}}),E=new _e({props:{code:"aW1wb3J0JTIwdG9yY2glMEFmcm9tJTIwZGlmZnVzZXJzJTIwaW1wb3J0JTIwSHVueXVhbkltYWdlUGlwZWxpbmUlMEElMEFwaXBlJTIwJTNEJTIwSHVueXVhbkltYWdlUGlwZWxpbmUuZnJvbV9wcmV0cmFpbmVkKCUwQSUyMCUyMCUyMCUyMCUyMmh1bnl1YW52aWRlby1jb21tdW5pdHklMkZIdW55dWFuSW1hZ2UtMi4xLURpZmZ1c2VycyUyMiUyQyUyMCUwQSUyMCUyMCUyMCUyMHRvcmNoX2R0eXBlJTNEdG9yY2guYmZsb2F0MTYlMEEpJTBBcGlwZSUyMCUzRCUyMHBpcGUudG8oJTIyY3VkYSUyMik=",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> HunyuanImagePipeline

pipe = HunyuanImagePipeline.from_pretrained(
    <span class="hljs-string">&quot;hunyuanvideo-community/HunyuanImage-2.1-Diffusers&quot;</span>, 
    torch_dtype=torch.bfloat16
)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)`,wrap:!1}}),N=new _e({props:{code:"cGlwZS5ndWlkZXIlMEE=",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.guider
AdaptiveProjectedMixGuidance {
  <span class="hljs-string">&quot;_class_name&quot;</span>: <span class="hljs-string">&quot;AdaptiveProjectedMixGuidance&quot;</span>,
  <span class="hljs-string">&quot;_diffusers_version&quot;</span>: <span class="hljs-string">&quot;0.36.0.dev0&quot;</span>,
  <span class="hljs-string">&quot;adaptive_projected_guidance_momentum&quot;</span>: -<span class="hljs-number">0.5</span>,
  <span class="hljs-string">&quot;adaptive_projected_guidance_rescale&quot;</span>: <span class="hljs-number">10.0</span>,
  <span class="hljs-string">&quot;adaptive_projected_guidance_scale&quot;</span>: <span class="hljs-number">10.0</span>,
  <span class="hljs-string">&quot;adaptive_projected_guidance_start_step&quot;</span>: <span class="hljs-number">5</span>,
  <span class="hljs-string">&quot;enabled&quot;</span>: true,
  <span class="hljs-string">&quot;eta&quot;</span>: <span class="hljs-number">0.0</span>,
  <span class="hljs-string">&quot;guidance_rescale&quot;</span>: <span class="hljs-number">0.0</span>,
  <span class="hljs-string">&quot;guidance_scale&quot;</span>: <span class="hljs-number">3.5</span>,
  <span class="hljs-string">&quot;start&quot;</span>: <span class="hljs-number">0.0</span>,
  <span class="hljs-string">&quot;stop&quot;</span>: <span class="hljs-number">1.0</span>,
  <span class="hljs-string">&quot;use_original_formulation&quot;</span>: false
}

State:
  step: <span class="hljs-literal">None</span>
  num_inference_steps: <span class="hljs-literal">None</span>
  timestep: <span class="hljs-literal">None</span>
  count_prepared: <span class="hljs-number">0</span>
  enabled: <span class="hljs-literal">True</span>
  num_conditions: <span class="hljs-number">2</span>
  momentum_buffer: <span class="hljs-literal">None</span>
  is_apg_enabled: <span class="hljs-literal">False</span>
  is_cfg_enabled: <span class="hljs-literal">True</span>`,wrap:!1}}),z=new _e({props:{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> HunyuanImagePipeline

pipe = HunyuanImagePipeline.from_pretrained(
    <span class="hljs-string">&quot;hunyuanvideo-community/HunyuanImage-2.1-Diffusers&quot;</span>, 
    torch_dtype=torch.bfloat16
)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

<span class="hljs-comment"># Update the guider configuration</span>
pipe.guider = pipe.guider.new(guidance_scale=<span class="hljs-number">5.0</span>)

prompt = (
    <span class="hljs-string">&quot;A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, &quot;</span>
    <span class="hljs-string">&quot;wearing a red knitted scarf and a red beret with the word &#x27;Tencent&#x27; on it, holding a paintbrush with a &quot;</span>
    <span class="hljs-string">&quot;focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style.&quot;</span>
)

image = pipe(
    prompt=prompt, 
    num_inference_steps=<span class="hljs-number">50</span>, 
    height=<span class="hljs-number">2048</span>, 
    width=<span class="hljs-number">2048</span>,
).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;image.png&quot;</span>)`,wrap:!1}}),Q=new fe({props:{title:"HunyuanImage-2.1-Distilled",local:"hunyuanimage-21-distilled",headingTag:"h2"}}),S=new _e({props:{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> HunyuanImagePipeline
pipe = HunyuanImagePipeline.from_pretrained(<span class="hljs-string">&quot;hunyuanvideo-community/HunyuanImage-2.1-Distilled-Diffusers&quot;</span>, torch_dtype=torch.bfloat16)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

prompt = (
    <span class="hljs-string">&quot;A cute, cartoon-style anthropomorphic penguin plush toy with fluffy fur, standing in a painting studio, &quot;</span>
    <span class="hljs-string">&quot;wearing a red knitted scarf and a red beret with the word &#x27;Tencent&#x27; on it, holding a paintbrush with a &quot;</span>
    <span class="hljs-string">&quot;focused expression as it paints an oil painting of the Mona Lisa, rendered in a photorealistic photographic style.&quot;</span>
)

out = pipe(
    prompt,
    num_inference_steps=<span class="hljs-number">8</span>,
    distilled_guidance_scale=<span class="hljs-number">3.25</span>,
    height=<span class="hljs-number">2048</span>,
    width=<span class="hljs-number">2048</span>,
    generator=generator,
).images[<span class="hljs-number">0</span>]
`,wrap:!1}}),Y=new fe({props:{title:"HunyuanImagePipeline",local:"diffusers.HunyuanImagePipeline",headingTag:"h2"}}),D=new oe({props:{name:"class diffusers.HunyuanImagePipeline",anchor:"diffusers.HunyuanImagePipeline",parameters:[{name:"scheduler",val:": FlowMatchEulerDiscreteScheduler"},{name:"vae",val:": AutoencoderKLHunyuanImage"},{name:"text_encoder",val:": Qwen2_5_VLForConditionalGeneration"},{name:"tokenizer",val:": Qwen2Tokenizer"},{name:"text_encoder_2",val:": T5EncoderModel"},{name:"tokenizer_2",val:": ByT5Tokenizer"},{name:"transformer",val:": HunyuanImageTransformer2DModel"},{name:"guider",val:": typing.Optional[diffusers.guiders.adaptive_projected_guidance_mix.AdaptiveProjectedMixGuidance] = None"},{name:"ocr_guider",val:": typing.Optional[diffusers.guiders.adaptive_projected_guidance_mix.AdaptiveProjectedMixGuidance] = None"}],parametersDescription:[{anchor:"diffusers.HunyuanImagePipeline.transformer",description:`<strong>transformer</strong> (<a href="/docs/diffusers/pr_12249/en/api/models/hunyuanimage_transformer_2d#diffusers.HunyuanImageTransformer2DModel">HunyuanImageTransformer2DModel</a>) &#x2014;
Conditional Transformer (MMDiT) architecture to denoise the encoded image latents.`,name:"transformer"},{anchor:"diffusers.HunyuanImagePipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/pr_12249/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler">FlowMatchEulerDiscreteScheduler</a>) &#x2014;
A scheduler to be used in combination with <code>transformer</code> to denoise the encoded image latents.`,name:"scheduler"},{anchor:"diffusers.HunyuanImagePipeline.vae",description:`<strong>vae</strong> (<a href="/docs/diffusers/pr_12249/en/api/models/autoencoder_kl_hunyuanimage#diffusers.AutoencoderKLHunyuanImage">AutoencoderKLHunyuanImage</a>) &#x2014;
Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.`,name:"vae"},{anchor:"diffusers.HunyuanImagePipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>Qwen2.5-VL-7B-Instruct</code>) &#x2014;
<a href="https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct" rel="nofollow">Qwen2.5-VL-7B-Instruct</a>, specifically the
<a href="https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct" rel="nofollow">Qwen2.5-VL-7B-Instruct</a> variant.`,name:"text_encoder"},{anchor:"diffusers.HunyuanImagePipeline.tokenizer",description:"<strong>tokenizer</strong> (<code>Qwen2Tokenizer</code>) &#x2014; Tokenizer of class [Qwen2Tokenizer].",name:"tokenizer"},{anchor:"diffusers.HunyuanImagePipeline.text_encoder_2",description:`<strong>text_encoder_2</strong> (<code>T5EncoderModel</code>) &#x2014;
<a href="https://huggingface.co/docs/transformers/en/model_doc/t5#transformers.T5EncoderModel" rel="nofollow">T5EncoderModel</a>
variant.`,name:"text_encoder_2"},{anchor:"diffusers.HunyuanImagePipeline.tokenizer_2",description:"<strong>tokenizer_2</strong> (<code>ByT5Tokenizer</code>) &#x2014; Tokenizer of class [ByT5Tokenizer]",name:"tokenizer_2"},{anchor:"diffusers.HunyuanImagePipeline.guider",description:`<strong>guider</strong> (<code>AdaptiveProjectedMixGuidance</code>) &#x2014;
[AdaptiveProjectedMixGuidance]to be used to guide the image generation.`,name:"guider"},{anchor:"diffusers.HunyuanImagePipeline.ocr_guider",description:`<strong>ocr_guider</strong> (<code>AdaptiveProjectedMixGuidance</code>, <em>optional</em>) &#x2014;
[AdaptiveProjectedMixGuidance] to be used to guide the image generation when text rendering is needed.`,name:"ocr_guider"}],source:"https://github.com/huggingface/diffusers/blob/vr_12249/src/diffusers/pipelines/hunyuan_image/pipeline_hunyuanimage.py#L158"}}),F=new oe({props:{name:"__call__",anchor:"diffusers.HunyuanImagePipeline.__call__",parameters:[{name:"prompt",val:": typing.Union[str, typing.List[str]] = None"},{name:"negative_prompt",val:": typing.Union[str, typing.List[str]] = None"},{name:"height",val:": typing.Optional[int] = None"},{name:"width",val:": typing.Optional[int] = None"},{name:"num_inference_steps",val:": int = 50"},{name:"distilled_guidance_scale",val:": typing.Optional[float] = 3.25"},{name:"sigmas",val:": typing.Optional[typing.List[float]] = None"},{name:"num_images_per_prompt",val:": int = 1"},{name:"generator",val:": typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None"},{name:"latents",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_embeds_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds_2",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds_mask_2",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_embeds_2",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_embeds_mask_2",val:": typing.Optional[torch.Tensor] = None"},{name:"output_type",val:": typing.Optional[str] = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"attention_kwargs",val:": typing.Optional[typing.Dict[str, typing.Any]] = None"},{name:"callback_on_step_end",val:": typing.Optional[typing.Callable[[int, int, typing.Dict], NoneType]] = None"},{name:"callback_on_step_end_tensor_inputs",val:": typing.List[str] = ['latents']"}],parametersDescription:[{anchor:"diffusers.HunyuanImagePipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide the image generation. If not defined, one has to pass <code>prompt_embeds</code>.
instead.`,name:"prompt"},{anchor:"diffusers.HunyuanImagePipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts not to guide the image generation. If not defined and negative_prompt_embeds is
not provided, will use an empty negative prompt. Ignored when not using guidance. ).`,name:"negative_prompt"},{anchor:"diffusers.HunyuanImagePipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to self.unet.config.sample_size * self.vae_scale_factor) &#x2014;
The height in pixels of the generated image. This is set to 1024 by default for the best results.`,name:"height"},{anchor:"diffusers.HunyuanImagePipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to self.unet.config.sample_size * self.vae_scale_factor) &#x2014;
The width in pixels of the generated image. This is set to 1024 by default for the best results.`,name:"width"},{anchor:"diffusers.HunyuanImagePipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 50) &#x2014;
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference.`,name:"num_inference_steps"},{anchor:"diffusers.HunyuanImagePipeline.__call__.sigmas",description:`<strong>sigmas</strong> (<code>List[float]</code>, <em>optional</em>) &#x2014;
Custom sigmas to use for the denoising process with schedulers which support a <code>sigmas</code> argument in
their <code>set_timesteps</code> method. If not defined, the default behavior when <code>num_inference_steps</code> is passed
will be used.`,name:"sigmas"},{anchor:"diffusers.HunyuanImagePipeline.__call__.distilled_guidance_scale",description:`<strong>distilled_guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to None) &#x2014;
A guidance scale value for guidance distilled models. Unlike the traditional classifier-free guidance
where the guidance scale is applied during inference through noise prediction rescaling, guidance
distilled models take the guidance scale directly as an input parameter during forward pass. Guidance
is enabled by setting <code>distilled_guidance_scale &gt; 1</code>. Higher guidance scale encourages to generate
images that are closely linked to the text <code>prompt</code>, usually at the expense of lower image quality. For
guidance distilled models, this parameter is required. For non-distilled models, this parameter will be
ignored.`,name:"distilled_guidance_scale"},{anchor:"diffusers.HunyuanImagePipeline.__call__.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
The number of images to generate per prompt.`,name:"num_images_per_prompt"},{anchor:"diffusers.HunyuanImagePipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code> or <code>List[torch.Generator]</code>, <em>optional</em>) &#x2014;
One or a list of <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow">torch generator(s)</a>
to make generation deterministic.`,name:"generator"},{anchor:"diffusers.HunyuanImagePipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor will be generated by sampling using the supplied random <code>generator</code>.`,name:"latents"},{anchor:"diffusers.HunyuanImagePipeline.__call__.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt weighting. If not
provided, text embeddings will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds"},{anchor:"diffusers.HunyuanImagePipeline.__call__.prompt_embeds_mask",description:`<strong>prompt_embeds_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings mask. Can be used to easily tweak text inputs, <em>e.g.</em> prompt weighting.
If not provided, text embeddings mask will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds_mask"},{anchor:"diffusers.HunyuanImagePipeline.__call__.prompt_embeds_2",description:`<strong>prompt_embeds_2</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings for ocr. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, text embeddings for ocr will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds_2"},{anchor:"diffusers.HunyuanImagePipeline.__call__.prompt_embeds_mask_2",description:`<strong>prompt_embeds_mask_2</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings mask for ocr. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, text embeddings mask for ocr will be generated from <code>prompt</code> input
argument.`,name:"prompt_embeds_mask_2"},{anchor:"diffusers.HunyuanImagePipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, negative_prompt_embeds will be generated from <code>negative_prompt</code> input
argument.`,name:"negative_prompt_embeds"},{anchor:"diffusers.HunyuanImagePipeline.__call__.negative_prompt_embeds_mask",description:`<strong>negative_prompt_embeds_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings mask. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, negative text embeddings mask will be generated from <code>negative_prompt</code>
input argument.`,name:"negative_prompt_embeds_mask"},{anchor:"diffusers.HunyuanImagePipeline.__call__.negative_prompt_embeds_2",description:`<strong>negative_prompt_embeds_2</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings for ocr. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, negative text embeddings for ocr will be generated from <code>negative_prompt</code>
input argument.`,name:"negative_prompt_embeds_2"},{anchor:"diffusers.HunyuanImagePipeline.__call__.negative_prompt_embeds_mask_2",description:`<strong>negative_prompt_embeds_mask_2</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings mask for ocr. Can be used to easily tweak text inputs, <em>e.g.</em>
prompt weighting. If not provided, negative text embeddings mask for ocr will be generated from
<code>negative_prompt</code> input argument.`,name:"negative_prompt_embeds_mask_2"},{anchor:"diffusers.HunyuanImagePipeline.__call__.output_type",description:`<strong>output_type</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;pil&quot;</code>) &#x2014;
The output format of the generate image. Choose between
<a href="https://pillow.readthedocs.io/en/stable/" rel="nofollow">PIL</a>: <code>PIL.Image.Image</code> or <code>np.array</code>.`,name:"output_type"},{anchor:"diffusers.HunyuanImagePipeline.__call__.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>~pipelines.qwenimage.QwenImagePipelineOutput</code> instead of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.HunyuanImagePipeline.__call__.attention_kwargs",description:`<strong>attention_kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
A kwargs dictionary that if specified is passed along to the <code>AttentionProcessor</code> as defined under
<code>self.processor</code> in
<a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py" rel="nofollow">diffusers.models.attention_processor</a>.`,name:"attention_kwargs"},{anchor:"diffusers.HunyuanImagePipeline.__call__.callback_on_step_end",description:`<strong>callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
A function that calls at the end of each denoising steps during the inference. The function is called
with the following arguments: <code>callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)</code>. <code>callback_kwargs</code> will include a list of all tensors as specified by
<code>callback_on_step_end_tensor_inputs</code>.`,name:"callback_on_step_end"},{anchor:"diffusers.HunyuanImagePipeline.__call__.callback_on_step_end_tensor_inputs",description:`<strong>callback_on_step_end_tensor_inputs</strong> (<code>List</code>, <em>optional</em>) &#x2014;
The list of tensor inputs for the <code>callback_on_step_end</code> function. The tensors specified in the list
will be passed as <code>callback_kwargs</code> argument. You will only be able to include variables listed in the
<code>._callback_tensor_inputs</code> attribute of your pipeline class.`,name:"callback_on_step_end_tensor_inputs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12249/src/diffusers/pipelines/hunyuan_image/pipeline_hunyuanimage.py#L502",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~pipelines.hunyuan_image.HunyuanImagePipelineOutput</code> if <code>return_dict</code> is True, otherwise a <code>tuple</code>. When
returning a tuple, the first element is a list with the generated images.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~pipelines.hunyuan_image.HunyuanImagePipelineOutput</code> or <code>tuple</code></p>
`}}),B=new gn({props:{anchor:"diffusers.HunyuanImagePipeline.__call__.example",$$slots:{default:[In]},$$scope:{ctx:ie}}}),O=new oe({props:{name:"encode_prompt",anchor:"diffusers.HunyuanImagePipeline.encode_prompt",parameters:[{name:"prompt",val:": typing.Union[str, typing.List[str]]"},{name:"device",val:": typing.Optional[torch.device] = None"},{name:"batch_size",val:": int = 1"},{name:"num_images_per_prompt",val:": int = 1"},{name:"prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds_2",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds_mask_2",val:": typing.Optional[torch.Tensor] = None"}],parametersDescription:[{anchor:"diffusers.HunyuanImagePipeline.encode_prompt.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
prompt to be encoded`,name:"prompt"},{anchor:"diffusers.HunyuanImagePipeline.encode_prompt.device",description:`<strong>device</strong> &#x2014; (<code>torch.device</code>):
torch device`,name:"device"},{anchor:"diffusers.HunyuanImagePipeline.encode_prompt.batch_size",description:`<strong>batch_size</strong> (<code>int</code>) &#x2014;
batch size of prompts, defaults to 1`,name:"batch_size"},{anchor:"diffusers.HunyuanImagePipeline.encode_prompt.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>) &#x2014;
number of images that should be generated per prompt`,name:"num_images_per_prompt"},{anchor:"diffusers.HunyuanImagePipeline.encode_prompt.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. If not provided, text embeddings will be generated from <code>prompt</code> input
argument.`,name:"prompt_embeds"},{anchor:"diffusers.HunyuanImagePipeline.encode_prompt.prompt_embeds_mask",description:`<strong>prompt_embeds_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text mask. If not provided, text mask will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds_mask"},{anchor:"diffusers.HunyuanImagePipeline.encode_prompt.prompt_embeds_2",description:`<strong>prompt_embeds_2</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated glyph text embeddings from ByT5. If not provided, will be generated from <code>prompt</code> input
argument using self.tokenizer_2 and self.text_encoder_2.`,name:"prompt_embeds_2"},{anchor:"diffusers.HunyuanImagePipeline.encode_prompt.prompt_embeds_mask_2",description:`<strong>prompt_embeds_mask_2</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated glyph text mask from ByT5. If not provided, will be generated from <code>prompt</code> input
argument using self.tokenizer_2 and self.text_encoder_2.`,name:"prompt_embeds_mask_2"}],source:"https://github.com/huggingface/diffusers/blob/vr_12249/src/diffusers/pipelines/hunyuan_image/pipeline_hunyuanimage.py#L294"}}),A=new fe({props:{title:"HunyuanImageRefinerPipeline",local:"diffusers.HunyuanImageRefinerPipeline",headingTag:"h2"}}),K=new oe({props:{name:"class diffusers.HunyuanImageRefinerPipeline",anchor:"diffusers.HunyuanImageRefinerPipeline",parameters:[{name:"scheduler",val:": FlowMatchEulerDiscreteScheduler"},{name:"vae",val:": AutoencoderKLHunyuanImageRefiner"},{name:"text_encoder",val:": Qwen2_5_VLForConditionalGeneration"},{name:"tokenizer",val:": Qwen2Tokenizer"},{name:"transformer",val:": HunyuanImageTransformer2DModel"},{name:"guider",val:": typing.Optional[diffusers.guiders.adaptive_projected_guidance_mix.AdaptiveProjectedMixGuidance] = None"}],parametersDescription:[{anchor:"diffusers.HunyuanImageRefinerPipeline.transformer",description:`<strong>transformer</strong> (<a href="/docs/diffusers/pr_12249/en/api/models/hunyuanimage_transformer_2d#diffusers.HunyuanImageTransformer2DModel">HunyuanImageTransformer2DModel</a>) &#x2014;
Conditional Transformer (MMDiT) architecture to denoise the encoded image latents.`,name:"transformer"},{anchor:"diffusers.HunyuanImageRefinerPipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/pr_12249/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler">FlowMatchEulerDiscreteScheduler</a>) &#x2014;
A scheduler to be used in combination with <code>transformer</code> to denoise the encoded image latents.`,name:"scheduler"},{anchor:"diffusers.HunyuanImageRefinerPipeline.vae",description:`<strong>vae</strong> (<a href="/docs/diffusers/pr_12249/en/api/models/autoencoder_kl_hunyuanimage_refiner#diffusers.AutoencoderKLHunyuanImageRefiner">AutoencoderKLHunyuanImageRefiner</a>) &#x2014;
Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.`,name:"vae"},{anchor:"diffusers.HunyuanImageRefinerPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>Qwen2.5-VL-7B-Instruct</code>) &#x2014;
<a href="https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct" rel="nofollow">Qwen2.5-VL-7B-Instruct</a>, specifically the
<a href="https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct" rel="nofollow">Qwen2.5-VL-7B-Instruct</a> variant.`,name:"text_encoder"},{anchor:"diffusers.HunyuanImageRefinerPipeline.tokenizer",description:"<strong>tokenizer</strong> (<code>Qwen2Tokenizer</code>) &#x2014; Tokenizer of class [Qwen2Tokenizer].",name:"tokenizer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12249/src/diffusers/pipelines/hunyuan_image/pipeline_hunyuanimage_refiner.py#L136"}}),ee=new oe({props:{name:"__call__",anchor:"diffusers.HunyuanImageRefinerPipeline.__call__",parameters:[{name:"prompt",val:": typing.Union[str, typing.List[str]] = None"},{name:"negative_prompt",val:": typing.Union[str, typing.List[str]] = None"},{name:"distilled_guidance_scale",val:": typing.Optional[float] = 3.25"},{name:"image",val:": typing.Union[PIL.Image.Image, numpy.ndarray, torch.Tensor, typing.List[PIL.Image.Image], typing.List[numpy.ndarray], typing.List[torch.Tensor], NoneType] = None"},{name:"height",val:": typing.Optional[int] = None"},{name:"width",val:": typing.Optional[int] = None"},{name:"num_inference_steps",val:": int = 4"},{name:"sigmas",val:": typing.Optional[typing.List[float]] = None"},{name:"num_images_per_prompt",val:": int = 1"},{name:"generator",val:": typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None"},{name:"latents",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_embeds_mask",val:": typing.Optional[torch.Tensor] = None"},{name:"output_type",val:": typing.Optional[str] = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"attention_kwargs",val:": typing.Optional[typing.Dict[str, typing.Any]] = None"},{name:"callback_on_step_end",val:": typing.Optional[typing.Callable[[int, int, typing.Dict], NoneType]] = None"},{name:"callback_on_step_end_tensor_inputs",val:": typing.List[str] = ['latents']"}],parametersDescription:[{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to guide the image generation. If not defined, one has to pass <code>prompt_embeds</code>.
instead.`,name:"prompt"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts not to guide the image generation. If not defined, will use an empty negative
prompt. Ignored when not using guidance.`,name:"negative_prompt"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.distilled_guidance_scale",description:`<strong>distilled_guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to None) &#x2014;
A guidance scale value for guidance distilled models. Unlike the traditional classifier-free guidance
where the guidance scale is applied during inference through noise prediction rescaling, guidance
distilled models take the guidance scale directly as an input parameter during forward pass. Guidance
is enabled by setting <code>distilled_guidance_scale &gt; 1</code>. Higher guidance scale encourages to generate
images that are closely linked to the text <code>prompt</code>, usually at the expense of lower image quality. For
guidance distilled models, this parameter is required. For non-distilled models, this parameter will be
ignored.`,name:"distilled_guidance_scale"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.num_images_per_prompt",description:"<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;",name:"num_images_per_prompt"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to self.unet.config.sample_size * self.vae_scale_factor) &#x2014;
The height in pixels of the generated image. This is set to 1024 by default for the best results.`,name:"height"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to self.unet.config.sample_size * self.vae_scale_factor) &#x2014;
The width in pixels of the generated image. This is set to 1024 by default for the best results.`,name:"width"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 50) &#x2014;
The number of denoising steps. More denoising steps usually lead to a higher quality image at the
expense of slower inference.`,name:"num_inference_steps"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.sigmas",description:`<strong>sigmas</strong> (<code>List[float]</code>, <em>optional</em>) &#x2014;
Custom sigmas to use for the denoising process with schedulers which support a <code>sigmas</code> argument in
their <code>set_timesteps</code> method. If not defined, the default behavior when <code>num_inference_steps</code> is passed
will be used.`,name:"sigmas"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
The number of images to generate per prompt.`,name:"num_images_per_prompt"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code> or <code>List[torch.Generator]</code>, <em>optional</em>) &#x2014;
One or a list of <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow">torch generator(s)</a>
to make generation deterministic.`,name:"generator"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
tensor will be generated by sampling using the supplied random <code>generator</code>.`,name:"latents"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt weighting. If not
provided, text embeddings will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, negative_prompt_embeds will be generated from <code>negative_prompt</code> input
argument.`,name:"negative_prompt_embeds"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.output_type",description:`<strong>output_type</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;pil&quot;</code>) &#x2014;
The output format of the generate image. Choose between
<a href="https://pillow.readthedocs.io/en/stable/" rel="nofollow">PIL</a>: <code>PIL.Image.Image</code> or <code>np.array</code>.`,name:"output_type"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.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>~pipelines.qwenimage.QwenImagePipelineOutput</code> instead of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.attention_kwargs",description:`<strong>attention_kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
A kwargs dictionary that if specified is passed along to the <code>AttentionProcessor</code> as defined under
<code>self.processor</code> in
<a href="https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py" rel="nofollow">diffusers.models.attention_processor</a>.`,name:"attention_kwargs"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.callback_on_step_end",description:`<strong>callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
A function that calls at the end of each denoising steps during the inference. The function is called
with the following arguments: <code>callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)</code>. <code>callback_kwargs</code> will include a list of all tensors as specified by
<code>callback_on_step_end_tensor_inputs</code>.`,name:"callback_on_step_end"},{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.callback_on_step_end_tensor_inputs",description:`<strong>callback_on_step_end_tensor_inputs</strong> (<code>List</code>, <em>optional</em>) &#x2014;
The list of tensor inputs for the <code>callback_on_step_end</code> function. The tensors specified in the list
will be passed as <code>callback_kwargs</code> argument. You will only be able to include variables listed in the
<code>._callback_tensor_inputs</code> attribute of your pipeline class.`,name:"callback_on_step_end_tensor_inputs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12249/src/diffusers/pipelines/hunyuan_image/pipeline_hunyuanimage_refiner.py#L434",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~pipelines.hunyuan_image.HunyuanImagePipelineOutput</code> if <code>return_dict</code> is True, otherwise a <code>tuple</code>. When
returning a tuple, the first element is a list with the generated images.</p>
`,returnType:`<script context="module">export const metadata = 'undefined';<\/script>


<p><code>~pipelines.hunyuan_image.HunyuanImagePipelineOutput</code> or <code>tuple</code></p>
`}}),P=new gn({props:{anchor:"diffusers.HunyuanImageRefinerPipeline.__call__.example",$$slots:{default:[vn]},$$scope:{ctx:ie}}}),ne=new oe({props:{name:"encode_prompt",anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt",parameters:[{name:"prompt",val:": typing.Union[str, typing.List[str], NoneType] = None"},{name:"device",val:": typing.Optional[torch.device] = None"},{name:"batch_size",val:": int = 1"},{name:"num_images_per_prompt",val:": int = 1"},{name:"prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"prompt_embeds_mask",val:": typing.Optional[torch.Tensor] = None"}],parametersDescription:[{anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
prompt to be encoded`,name:"prompt"},{anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt.device",description:`<strong>device</strong> &#x2014; (<code>torch.device</code>):
torch device`,name:"device"},{anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt.batch_size",description:`<strong>batch_size</strong> (<code>int</code>) &#x2014;
batch size of prompts, defaults to 1`,name:"batch_size"},{anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>) &#x2014;
number of images that should be generated per prompt`,name:"num_images_per_prompt"},{anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. If not provided, text embeddings will be generated from <code>prompt</code> input
argument.`,name:"prompt_embeds"},{anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt.prompt_embeds_mask",description:`<strong>prompt_embeds_mask</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text mask. If not provided, text mask will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds_mask"},{anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt.prompt_embeds_2",description:`<strong>prompt_embeds_2</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated glyph text embeddings from ByT5. If not provided, will be generated from <code>prompt</code> input
argument using self.tokenizer_2 and self.text_encoder_2.`,name:"prompt_embeds_2"},{anchor:"diffusers.HunyuanImageRefinerPipeline.encode_prompt.prompt_embeds_mask_2",description:`<strong>prompt_embeds_mask_2</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated glyph text mask from ByT5. If not provided, will be generated from <code>prompt</code> input
argument using self.tokenizer_2 and self.text_encoder_2.`,name:"prompt_embeds_mask_2"}],source:"https://github.com/huggingface/diffusers/blob/vr_12249/src/diffusers/pipelines/hunyuan_image/pipeline_hunyuanimage_refiner.py#L223"}}),te=new fe({props:{title:"HunyuanImagePipelineOutput",local:"diffusers.pipelines.hunyuan_image.pipeline_output.HunyuanImagePipelineOutput",headingTag:"h2"}}),ae=new oe({props:{name:"class diffusers.pipelines.hunyuan_image.pipeline_output.HunyuanImagePipelineOutput",anchor:"diffusers.pipelines.hunyuan_image.pipeline_output.HunyuanImagePipelineOutput",parameters:[{name:"images",val:": typing.Union[typing.List[PIL.Image.Image], numpy.ndarray]"}],parametersDescription:[{anchor:"diffusers.pipelines.hunyuan_image.pipeline_output.HunyuanImagePipelineOutput.images",description:`<strong>images</strong> (<code>List[PIL.Image.Image]</code> or <code>np.ndarray</code>) &#x2014;
List of denoised PIL images of length <code>batch_size</code> or numpy array of shape <code>(batch_size, height, width, num_channels)</code>. PIL images or numpy array present the denoised images of the diffusion pipeline.`,name:"images"}],source:"https://github.com/huggingface/diffusers/blob/vr_12249/src/diffusers/pipelines/hunyuan_image/pipeline_output.py#L11"}}),se=new Mn({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/hunyuanimage21.md"}}),{c(){r=l("meta"),U=s(),b=l("p"),h=s(),d(y.$$.fragment),i=s(),w=l("p"),w.textContent=Ae,ye=s(),C=l("p"),C.textContent=Ke,be=s(),G=l("table"),G.innerHTML=en,we=s(),W=l("blockquote"),W.innerHTML=nn,Me=s(),d(R.$$.fragment),Ie=s(),V=l("p"),V.innerHTML=tn,ve=s(),d(E.$$.fragment),Te=s(),L=l("p"),L.innerHTML=an,Ue=s(),d(N.$$.fragment),je=s(),q=l("p"),q.innerHTML=sn,xe=s(),d(z.$$.fragment),ke=s(),d(Q.$$.fragment),He=s(),X=l("p"),X.innerHTML=on,Je=s(),d(S.$$.fragment),$e=s(),d(Y.$$.fragment),Be=s(),I=l("div"),d(D.$$.fragment),Le=s(),re=l("p"),re.textContent=rn,Ne=s(),j=l("div"),d(F.$$.fragment),qe=s(),le=l("p"),le.textContent=ln,ze=s(),d(B.$$.fragment),Qe=s(),pe=l("div"),d(O.$$.fragment),Pe=s(),d(A.$$.fragment),Ze=s(),v=l("div"),d(K.$$.fragment),Xe=s(),de=l("p"),de.textContent=pn,Se=s(),x=l("div"),d(ee.$$.fragment),Ye=s(),me=l("p"),me.textContent=dn,De=s(),d(P.$$.fragment),Fe=s(),ce=l("div"),d(ne.$$.fragment),Ce=s(),d(te.$$.fragment),Ge=s(),k=l("div"),d(ae.$$.fragment),Oe=s(),ue=l("p"),ue.textContent=mn,We=s(),d(se.$$.fragment),Re=s(),he=l("p"),this.h()},l(e){const n=wn("svelte-u9bgzb",document.head);r=p(n,"META",{name:!0,content:!0}),n.forEach(t),U=o(e),b=p(e,"P",{}),J(b).forEach(t),h=o(e),m(y.$$.fragment,e),i=o(e),w=p(e,"P",{"data-svelte-h":!0}),M(w)!=="svelte-vdpxxc"&&(w.textContent=Ae),ye=o(e),C=p(e,"P",{"data-svelte-h":!0}),M(C)!=="svelte-pxcomv"&&(C.textContent=Ke),be=o(e),G=p(e,"TABLE",{"data-svelte-h":!0}),M(G)!=="svelte-1cogr90"&&(G.innerHTML=en),we=o(e),W=p(e,"BLOCKQUOTE",{"data-svelte-h":!0}),M(W)!=="svelte-41zj9c"&&(W.innerHTML=nn),Me=o(e),m(R.$$.fragment,e),Ie=o(e),V=p(e,"P",{"data-svelte-h":!0}),M(V)!=="svelte-1e88cdr"&&(V.innerHTML=tn),ve=o(e),m(E.$$.fragment,e),Te=o(e),L=p(e,"P",{"data-svelte-h":!0}),M(L)!=="svelte-mdk92"&&(L.innerHTML=an),Ue=o(e),m(N.$$.fragment,e),je=o(e),q=p(e,"P",{"data-svelte-h":!0}),M(q)!=="svelte-uze9an"&&(q.innerHTML=sn),xe=o(e),m(z.$$.fragment,e),ke=o(e),m(Q.$$.fragment,e),He=o(e),X=p(e,"P",{"data-svelte-h":!0}),M(X)!=="svelte-yz3ezo"&&(X.innerHTML=on),Je=o(e),m(S.$$.fragment,e),$e=o(e),m(Y.$$.fragment,e),Be=o(e),I=p(e,"DIV",{class:!0});var T=J(I);m(D.$$.fragment,T),Le=o(T),re=p(T,"P",{"data-svelte-h":!0}),M(re)!=="svelte-o9b5ts"&&(re.textContent=rn),Ne=o(T),j=p(T,"DIV",{class:!0});var H=J(j);m(F.$$.fragment,H),qe=o(H),le=p(H,"P",{"data-svelte-h":!0}),M(le)!=="svelte-v78lg8"&&(le.textContent=ln),ze=o(H),m(B.$$.fragment,H),H.forEach(t),Qe=o(T),pe=p(T,"DIV",{class:!0});var cn=J(pe);m(O.$$.fragment,cn),cn.forEach(t),T.forEach(t),Pe=o(e),m(A.$$.fragment,e),Ze=o(e),v=p(e,"DIV",{class:!0});var Z=J(v);m(K.$$.fragment,Z),Xe=o(Z),de=p(Z,"P",{"data-svelte-h":!0}),M(de)!=="svelte-o9b5ts"&&(de.textContent=pn),Se=o(Z),x=p(Z,"DIV",{class:!0});var ge=J(x);m(ee.$$.fragment,ge),Ye=o(ge),me=p(ge,"P",{"data-svelte-h":!0}),M(me)!=="svelte-v78lg8"&&(me.textContent=dn),De=o(ge),m(P.$$.fragment,ge),ge.forEach(t),Fe=o(Z),ce=p(Z,"DIV",{class:!0});var un=J(ce);m(ne.$$.fragment,un),un.forEach(t),Z.forEach(t),Ce=o(e),m(te.$$.fragment,e),Ge=o(e),k=p(e,"DIV",{class:!0});var Ee=J(k);m(ae.$$.fragment,Ee),Oe=o(Ee),ue=p(Ee,"P",{"data-svelte-h":!0}),M(ue)!=="svelte-1gqdyq4"&&(ue.textContent=mn),Ee.forEach(t),We=o(e),m(se.$$.fragment,e),Re=o(e),he=p(e,"P",{}),J(he).forEach(t),this.h()},h(){$(r,"name","hf:doc:metadata"),$(r,"content",Un),$(j,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(pe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(I,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(x,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(ce,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(v,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(e,n){_(document.head,r),a(e,U,n),a(e,b,n),a(e,h,n),c(y,e,n),a(e,i,n),a(e,w,n),a(e,ye,n),a(e,C,n),a(e,be,n),a(e,G,n),a(e,we,n),a(e,W,n),a(e,Me,n),c(R,e,n),a(e,Ie,n),a(e,V,n),a(e,ve,n),c(E,e,n),a(e,Te,n),a(e,L,n),a(e,Ue,n),c(N,e,n),a(e,je,n),a(e,q,n),a(e,xe,n),c(z,e,n),a(e,ke,n),c(Q,e,n),a(e,He,n),a(e,X,n),a(e,Je,n),c(S,e,n),a(e,$e,n),c(Y,e,n),a(e,Be,n),a(e,I,n),c(D,I,null),_(I,Le),_(I,re),_(I,Ne),_(I,j),c(F,j,null),_(j,qe),_(j,le),_(j,ze),c(B,j,null),_(I,Qe),_(I,pe),c(O,pe,null),a(e,Pe,n),c(A,e,n),a(e,Ze,n),a(e,v,n),c(K,v,null),_(v,Xe),_(v,de),_(v,Se),_(v,x),c(ee,x,null),_(x,Ye),_(x,me),_(x,De),c(P,x,null),_(v,Fe),_(v,ce),c(ne,ce,null),a(e,Ce,n),c(te,e,n),a(e,Ge,n),a(e,k,n),c(ae,k,null),_(k,Oe),_(k,ue),a(e,We,n),c(se,e,n),a(e,Re,n),a(e,he,n),Ve=!0},p(e,[n]){const T={};n&2&&(T.$$scope={dirty:n,ctx:e}),B.$set(T);const H={};n&2&&(H.$$scope={dirty:n,ctx:e}),P.$set(H)},i(e){Ve||(u(y.$$.fragment,e),u(R.$$.fragment,e),u(E.$$.fragment,e),u(N.$$.fragment,e),u(z.$$.fragment,e),u(Q.$$.fragment,e),u(S.$$.fragment,e),u(Y.$$.fragment,e),u(D.$$.fragment,e),u(F.$$.fragment,e),u(B.$$.fragment,e),u(O.$$.fragment,e),u(A.$$.fragment,e),u(K.$$.fragment,e),u(ee.$$.fragment,e),u(P.$$.fragment,e),u(ne.$$.fragment,e),u(te.$$.fragment,e),u(ae.$$.fragment,e),u(se.$$.fragment,e),Ve=!0)},o(e){g(y.$$.fragment,e),g(R.$$.fragment,e),g(E.$$.fragment,e),g(N.$$.fragment,e),g(z.$$.fragment,e),g(Q.$$.fragment,e),g(S.$$.fragment,e),g(Y.$$.fragment,e),g(D.$$.fragment,e),g(F.$$.fragment,e),g(B.$$.fragment,e),g(O.$$.fragment,e),g(A.$$.fragment,e),g(K.$$.fragment,e),g(ee.$$.fragment,e),g(P.$$.fragment,e),g(ne.$$.fragment,e),g(te.$$.fragment,e),g(ae.$$.fragment,e),g(se.$$.fragment,e),Ve=!1},d(e){e&&(t(U),t(b),t(h),t(i),t(w),t(ye),t(C),t(be),t(G),t(we),t(W),t(Me),t(Ie),t(V),t(ve),t(Te),t(L),t(Ue),t(je),t(q),t(xe),t(ke),t(He),t(X),t(Je),t($e),t(Be),t(I),t(Pe),t(Ze),t(v),t(Ce),t(Ge),t(k),t(We),t(Re),t(he)),t(r),f(y,e),f(R,e),f(E,e),f(N,e),f(z,e),f(Q,e),f(S,e),f(Y,e),f(D),f(F),f(B),f(O),f(A,e),f(K),f(ee),f(P),f(ne),f(te,e),f(ae),f(se,e)}}}const Un='{"title":"HunyuanImage2.1","local":"hunyuanimage21","sections":[{"title":"HunyuanImage-2.1","local":"hunyuanimage-21","sections":[],"depth":2},{"title":"HunyuanImage-2.1-Distilled","local":"hunyuanimage-21-distilled","sections":[],"depth":2},{"title":"HunyuanImagePipeline","local":"diffusers.HunyuanImagePipeline","sections":[],"depth":2},{"title":"HunyuanImageRefinerPipeline","local":"diffusers.HunyuanImageRefinerPipeline","sections":[],"depth":2},{"title":"HunyuanImagePipelineOutput","local":"diffusers.pipelines.hunyuan_image.pipeline_output.HunyuanImagePipelineOutput","sections":[],"depth":2}],"depth":1}';function jn(ie){return hn(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Pn extends yn{constructor(r){super(),bn(this,r,jn,Tn,_n,{})}}export{Pn as component};