diffusers/pr_13896/en/_app/immutable/nodes/149.99310ce0.js

import{s as Vt,n as Ht,o as Rt}from"../chunks/scheduler.53228c21.js";import{S as Qt,i as zt,e as r,s as n,c as d,h as Ft,a as o,d as i,b as a,f as ie,g as c,j as p,k as T,l,m as s,n as u,t as g,o as f,p as h}from"../chunks/index.cac5d66a.js";import{C as Xt}from"../chunks/CopyLLMTxtMenu.f1196f8c.js";import{D as ye}from"../chunks/Docstring.0935d2db.js";import{C as et}from"../chunks/CodeBlock.606cbaf4.js";import{H as J,E as Yt}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.05c95d6f.js";function St(_t){let b,be,_e,we,I,Te,$,Je,j,Mt=`DreamLite is a text-to-image and image-editing model from ByteDance. It pairs a custom 2D U-Net
(<code>DreamLiteUNetModel</code>) with the <code>Qwen3-VL</code> multimodal encoder as its prompt / image-instruction encoder,
and uses an <code>AutoencoderTiny</code> (TAESD-style) VAE for fast latent encode/decode.`,ve,D,yt="Two pipelines are exposed:",Le,Z,bt='<thead><tr><th>Pipeline</th> <th>Modes</th> <th>CFG</th> <th>Use case</th></tr></thead> <tbody><tr><td><a href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipeline">DreamLitePipeline</a></td> <td>text-to-image <strong>and</strong> image-editing (auto-selected by whether <code>image</code> is <code>None</code>)</td> <td>3-branch dual CFG (<code>guidance_scale</code> on text branch, <code>image_guidance_scale</code> on image branch, à la InstructPix2Pix)</td> <td>Highest quality</td></tr> <tr><td><a href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLiteMobilePipeline">DreamLiteMobilePipeline</a></td> <td>text-to-image <strong>and</strong> image-editing (auto-selected by whether <code>image</code> is <code>None</code>)</td> <td>None — distilled, single UNet forward per step</td> <td>On-device / low-latency</td></tr></tbody>',xe,P,wt="Official checkpoints:",Ue,C,Tt='<li>Base model: <a href="https://huggingface.co/carlofkl/DreamLite-base" rel="nofollow">carlofkl/DreamLite-base</a></li> <li>Distilled mobile model: <a href="https://huggingface.co/carlofkl/DreamLite-mobile" rel="nofollow">carlofkl/DreamLite-mobile</a></li>',Ie,v,Jt=`<p>Both pipelines auto-detect text-to-image vs. image-editing mode from whether the <code>image</code> argument is
provided. There is no separate <code>Img2Img</code> class.</p>`,$e,L,vt=`<p>When loading an input image for editing, prefer <code>diffusers.utils.load_image(...)</code> over raw <code>PIL.Image.open(...)</code>.
<code>load_image</code> enforces an RGB conversion and applies EXIF orientation, both of which the pipeline assumes.
A plain <code>Image.open</code> of an RGBA / palette / EXIF-rotated source will silently produce a different latent
conditioning and degrade output quality.</p>`,je,G,De,W,Ze,k,Pe,N,Lt=`Pass an <code>image</code> to enter edit mode. Both <code>guidance_scale</code> (text branch) and <code>image_guidance_scale</code>
(image branch) are active here.`,Ce,E,Ge,q,We,B,xt=`The mobile pipeline is distilled and skips CFG entirely — a single UNet forward per step. It accepts the
same <code>prompt</code> / <code>height</code> / <code>width</code> / <code>num_inference_steps</code> arguments, but <strong>ignores</strong> <code>guidance_scale</code> and
<code>image_guidance_scale</code> if passed (a warning is logged).`,ke,V,Ne,H,Ee,R,qe,Q,Be,z,Ut=`<li>Both pipelines force <code>batch_size = 1</code> internally; <code>num_images_per_prompt</code> controls how many samples
are drawn from the same prompt rather than parallel batching.</li> <li>The prompt encoder is <code>Qwen3-VL</code>, which is a multimodal model. Loading the full pipeline therefore
requires sufficient GPU memory for both the U-Net and the Qwen3-VL text encoder (~4 GB + ~0.7 GB
in bf16 for the base release).</li> <li>The VAE is <code>AutoencoderTiny</code> and exposes <code>encoder_block_out_channels</code>; <code>vae_scale_factor</code> is derived
from it at pipeline init time.</li>`,Ve,F,He,_,X,tt,ne,It="DreamLite pipeline for text-to-image and instruction-based image editing.",it,ae,$t="The same pipeline supports both modes; the operating mode is auto-detected from the inputs:",nt,se,jt="<li><code>image is None</code> -&gt; text-to-image (single CFG on text).</li> <li><code>image is not None</code> -&gt; image-to-image / instruction edit (dual CFG: text + image).</li>",at,le,Dt=`Components:
text_encoder ([<em>~transformers.Qwen3VLForConditionalGeneration</em>]):
Multimodal text/vision encoder used to produce conditioning embeddings.
tokenizer ([<em>~transformers.AutoTokenizer</em>]):
Tokenizer for text-only (generate) mode.
processor ([<em>~transformers.Qwen3VLProcessor</em>]):
Multimodal processor for edit mode (text + image template).
vae ([<em>~diffusers.AutoencoderTiny</em>]):
Mobile-friendly tiny VAE for latent encode/decode.
unet ([<em>~diffusers.DreamLiteUNetModel</em>]):
DreamLite UNet (GQA + qk_norm + depthwise-separable convs).
scheduler ([<em>~diffusers.FlowMatchEulerDiscreteScheduler</em>]):
Flow-matching Euler scheduler with dynamic shift.`,st,re,Zt=`Note:
<code>batch_size</code> is currently forced to <code>1</code>; <code>num_images_per_prompt</code> is supported.`,lt,x,Y,rt,oe,Pt="Run the DreamLite pipeline.",Re,S,Qe,m,A,ot,pe,Ct=`DreamLite <strong>Mobile</strong> pipeline: a distilled, classifier-free-guidance-free variant of
<a href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipeline">DreamLitePipeline</a> for fast few-step inference (default 4 steps).`,pt,me,Gt="The operating mode is auto-detected from inputs (same as the base pipeline):",mt,de,Wt="<li><code>image is None</code> -&gt; text-to-image.</li> <li><code>image is not None</code> -&gt; image-to-image / instruction edit.</li>",dt,ce,kt=`Because classifier-free guidance is <strong>distilled away</strong>, <code>guidance_scale</code> and <code>image_guidance_scale</code> are
accepted for API parity with <a href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipeline">DreamLitePipeline</a> but are ignored in the denoising loop. <code>negative_prompt</code>
is intentionally absent.`,ct,ue,Nt=`Components (identical to the base pipeline):
text_encoder ([<em>~transformers.Qwen3VLForConditionalGeneration</em>]):
Multimodal text/vision encoder.
tokenizer ([<em>~transformers.AutoTokenizer</em>]):
Tokenizer for text-only (generate) mode.
processor ([<em>~transformers.Qwen3VLProcessor</em>]):
Multimodal processor for edit mode.
vae ([<em>~diffusers.AutoencoderTiny</em>]):
Mobile-friendly tiny VAE.
unet ([<em>~diffusers.DreamLiteUNetModel</em>]):
DreamLite UNet.
scheduler ([<em>~diffusers.FlowMatchEulerDiscreteScheduler</em>]):
Flow-matching Euler scheduler with dynamic shift.`,ut,ge,Et=`Note:
<code>batch_size</code> is currently forced to <code>1</code>; <code>num_images_per_prompt</code> is supported.`,gt,U,O,ft,fe,qt="Run the distilled DreamLite Mobile pipeline.",ze,K,Fe,w,ee,ht,he,Bt="Output class for DreamLite pipelines.",Xe,te,Ye,Me,Se;return I=new Xt({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),$=new J({props:{title:"DreamLite",local:"dreamlite",headingTag:"h1"}}),G=new J({props:{title:"Text-to-image (Base)",local:"text-to-image-base",headingTag:"h2"}}),W=new et({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> DreamLitePipeline

pipe = DreamLitePipeline.from_pretrained(<span class="hljs-string">&quot;carlofkl/DreamLite-base&quot;</span>, revision=<span class="hljs-string">&quot;diffusers&quot;</span>, torch_dtype=torch.bfloat16)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

image = pipe(
    prompt=<span class="hljs-string">&quot;a dog running on the grass&quot;</span>,
    negative_prompt=<span class="hljs-string">&quot;&quot;</span>,
    height=<span class="hljs-number">1024</span>,
    width=<span class="hljs-number">1024</span>,
    num_inference_steps=<span class="hljs-number">28</span>,
    generator=torch.Generator(<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(<span class="hljs-number">42</span>),
).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;dreamlite_t2i.png&quot;</span>)`,lang:"python",wrap:!1}}),k=new J({props:{title:"Image editing (Base)",local:"image-editing-base",headingTag:"h2"}}),E=new et({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> DreamLitePipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

pipe = DreamLitePipeline.from_pretrained(<span class="hljs-string">&quot;carlofkl/DreamLite-base&quot;</span>, revision=<span class="hljs-string">&quot;diffusers&quot;</span>, torch_dtype=torch.bfloat16)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

source = load_image(<span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png&quot;</span>)

image = pipe(
    prompt=<span class="hljs-string">&quot;turn the cat into a corgi&quot;</span>,
    image=source,
    height=<span class="hljs-number">1024</span>,
    width=<span class="hljs-number">1024</span>,
    num_inference_steps=<span class="hljs-number">28</span>,
    generator=torch.Generator(<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(<span class="hljs-number">42</span>),
).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;dreamlite_edit.png&quot;</span>)`,lang:"python",wrap:!1}}),q=new J({props:{title:"Text-to-image (Mobile)",local:"text-to-image-mobile",headingTag:"h2"}}),V=new et({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> DreamLiteMobilePipeline

pipe = DreamLiteMobilePipeline.from_pretrained(<span class="hljs-string">&quot;carlofkl/DreamLite-mobile&quot;</span>, revision=<span class="hljs-string">&quot;diffusers&quot;</span>, torch_dtype=torch.bfloat16)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

image = pipe(
    prompt=<span class="hljs-string">&quot;a dog running on the grass&quot;</span>,
    height=<span class="hljs-number">1024</span>,
    width=<span class="hljs-number">1024</span>,
    num_inference_steps=<span class="hljs-number">4</span>,
    generator=torch.Generator(<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(<span class="hljs-number">42</span>),
).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;dreamlite_mobile_t2i.png&quot;</span>)`,lang:"python",wrap:!1}}),H=new J({props:{title:"Image editing (Mobile)",local:"image-editing-mobile",headingTag:"h2"}}),R=new et({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> DreamLiteMobilePipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image

pipe = DreamLiteMobilePipeline.from_pretrained(<span class="hljs-string">&quot;carlofkl/DreamLite-mobile&quot;</span>, revision=<span class="hljs-string">&quot;diffusers&quot;</span>, torch_dtype=torch.bfloat16)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

source = load_image(<span class="hljs-string">&quot;https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png&quot;</span>)

image = pipe(
    prompt=<span class="hljs-string">&quot;turn the cat into a corgi&quot;</span>,
    image=source,
    height=<span class="hljs-number">1024</span>,
    width=<span class="hljs-number">1024</span>,
    num_inference_steps=<span class="hljs-number">4</span>,
    generator=torch.Generator(<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(<span class="hljs-number">42</span>),
).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;dreamlite_mobile_edit.png&quot;</span>)`,lang:"python",wrap:!1}}),Q=new J({props:{title:"Notes and limitations",local:"notes-and-limitations",headingTag:"h2"}}),F=new J({props:{title:"DreamLitePipeline",local:"diffusers.DreamLitePipeline",headingTag:"h2"}}),X=new ye({props:{name:"class diffusers.DreamLitePipeline",anchor:"diffusers.DreamLitePipeline",parameters:[{name:"text_encoder",val:": Qwen3VLForConditionalGeneration"},{name:"tokenizer",val:": AutoTokenizer"},{name:"processor",val:": Qwen3VLProcessor"},{name:"vae",val:": AutoencoderTiny"},{name:"unet",val:": DreamLiteUNetModel"},{name:"scheduler",val:": FlowMatchEulerDiscreteScheduler"}],source:"https://github.com/huggingface/diffusers/blob/vr_13896/src/diffusers/pipelines/dreamlite/pipeline_dreamlite.py#L155"}}),Y=new ye({props:{name:"__call__",anchor:"diffusers.DreamLitePipeline.__call__",parameters:[{name:"prompt",val:": typing.Optional[str] = None"},{name:"negative_prompt",val:": typing.Optional[str] = None"},{name:"image",val:": typing.Optional[PIL.Image.Image] = None"},{name:"height",val:": typing.Optional[int] = None"},{name:"width",val:": typing.Optional[int] = None"},{name:"guidance_scale",val:": float = 3.5"},{name:"image_guidance_scale",val:": float = 1.5"},{name:"num_inference_steps",val:": int = 30"},{name:"sigmas",val:": typing.Optional[typing.List[float]] = None"},{name:"num_images_per_prompt",val:": typing.Optional[int] = 1"},{name:"generator",val:": typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None"},{name:"output_type",val:": typing.Optional[str] = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"max_sequence_length",val:": int = 200"},{name:"text_pad_embedding",val:": typing.Optional[torch.Tensor] = None"}],parametersDescription:[{anchor:"diffusers.DreamLitePipeline.__call__.prompt",description:"<strong>prompt</strong> &#x2014; Text prompt.",name:"prompt"},{anchor:"diffusers.DreamLitePipeline.__call__.negative_prompt",description:"<strong>negative_prompt</strong> &#x2014; Negative text prompt (defaults to empty string).",name:"negative_prompt"},{anchor:"diffusers.DreamLitePipeline.__call__.image",description:`<strong>image</strong> &#x2014; Optional input image. If provided, the pipeline runs in <strong>edit / image-to-image</strong> mode
with dual classifier-free guidance; otherwise it runs in <strong>text-to-image</strong> mode.`,name:"image"},{anchor:"diffusers.DreamLitePipeline.__call__.height",description:`<strong>height</strong> &#x2014; Output resolution (height). Defaults to <code>default_sample_size * vae_scale_factor</code> (1024).
The same default applies in both T2I and I2I; pass an explicit value to override.`,name:"height"},{anchor:"diffusers.DreamLitePipeline.__call__.width",description:`<strong>width</strong> &#x2014; Output resolution (width). Defaults to <code>default_sample_size * vae_scale_factor</code> (1024).
The same default applies in both T2I and I2I; pass an explicit value to override.`,name:"width"},{anchor:"diffusers.DreamLitePipeline.__call__.guidance_scale",description:"<strong>guidance_scale</strong> &#x2014; CFG scale on the text branch (both modes).",name:"guidance_scale"},{anchor:"diffusers.DreamLitePipeline.__call__.image_guidance_scale",description:"<strong>image_guidance_scale</strong> &#x2014; Additional CFG scale on the image branch (edit mode only).",name:"image_guidance_scale"},{anchor:"diffusers.DreamLitePipeline.__call__.num_inference_steps",description:"<strong>num_inference_steps</strong> &#x2014; Number of denoising steps.",name:"num_inference_steps"},{anchor:"diffusers.DreamLitePipeline.__call__.sigmas",description:"<strong>sigmas</strong> &#x2014; Optional explicit FlowMatch sigmas; defaults to a uniform linspace.",name:"sigmas"},{anchor:"diffusers.DreamLitePipeline.__call__.num_images_per_prompt",description:"<strong>num_images_per_prompt</strong> &#x2014; Output images per prompt (note: <code>batch_size</code> is forced to 1).",name:"num_images_per_prompt"},{anchor:"diffusers.DreamLitePipeline.__call__.generator",description:"<strong>generator</strong> &#x2014; Random generator(s).",name:"generator"},{anchor:"diffusers.DreamLitePipeline.__call__.output_type",description:"<strong>output_type</strong> &#x2014; <code>&quot;pil&quot;</code>, <code>&quot;np&quot;</code>, <code>&quot;pt&quot;</code> or <code>&quot;latent&quot;</code>.",name:"output_type"},{anchor:"diffusers.DreamLitePipeline.__call__.return_dict",description:'<strong>return_dict</strong> &#x2014; If True, returns a <a href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipelineOutput">DreamLitePipelineOutput</a>; else a tuple <code>(images,)</code>.',name:"return_dict"},{anchor:"diffusers.DreamLitePipeline.__call__.max_sequence_length",description:`<strong>max_sequence_length</strong> &#x2014; Maximum number of user-prompt tokens kept after dropping the chat-template
prefix. Only applies to <code>generate</code> mode (the <code>edit</code> mode uses the multimodal processor&#x2019;s native
padding).`,name:"max_sequence_length"},{anchor:"diffusers.DreamLitePipeline.__call__.text_pad_embedding",description:"<strong>text_pad_embedding</strong> &#x2014; Optional learned pad embedding for masked positions.",name:"text_pad_embedding"}],source:"https://github.com/huggingface/diffusers/blob/vr_13896/src/diffusers/pipelines/dreamlite/pipeline_dreamlite.py#L388",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p><a
  href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipelineOutput"
>DreamLitePipelineOutput</a> or <code>tuple</code>.</p>
`}}),S=new J({props:{title:"DreamLiteMobilePipeline",local:"diffusers.DreamLiteMobilePipeline",headingTag:"h2"}}),A=new ye({props:{name:"class diffusers.DreamLiteMobilePipeline",anchor:"diffusers.DreamLiteMobilePipeline",parameters:[{name:"text_encoder",val:": Qwen3VLForConditionalGeneration"},{name:"tokenizer",val:": AutoTokenizer"},{name:"processor",val:": Qwen3VLProcessor"},{name:"vae",val:": AutoencoderTiny"},{name:"unet",val:": DreamLiteUNetModel"},{name:"scheduler",val:": FlowMatchEulerDiscreteScheduler"}],source:"https://github.com/huggingface/diffusers/blob/vr_13896/src/diffusers/pipelines/dreamlite/pipeline_dreamlite_mobile.py#L156"}}),O=new ye({props:{name:"__call__",anchor:"diffusers.DreamLiteMobilePipeline.__call__",parameters:[{name:"prompt",val:": typing.Union[str, typing.List[str]] = None"},{name:"image",val:": typing.Optional[PIL.Image.Image] = None"},{name:"height",val:": typing.Optional[int] = None"},{name:"width",val:": typing.Optional[int] = None"},{name:"num_inference_steps",val:": int = 4"},{name:"guidance_scale",val:": typing.Optional[float] = None"},{name:"image_guidance_scale",val:": typing.Optional[float] = None"},{name:"sigmas",val:": typing.Optional[typing.List[float]] = None"},{name:"num_images_per_prompt",val:": typing.Optional[int] = 1"},{name:"generator",val:": typing.Union[torch._C.Generator, typing.List[torch._C.Generator], NoneType] = None"},{name:"output_type",val:": typing.Optional[str] = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"max_sequence_length",val:": int = 200"},{name:"text_pad_embedding",val:": typing.Optional[torch.Tensor] = None"}],parametersDescription:[{anchor:"diffusers.DreamLiteMobilePipeline.__call__.prompt",description:"<strong>prompt</strong> &#x2014; Text prompt.",name:"prompt"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.image",description:`<strong>image</strong> &#x2014; Optional input image. If provided, runs in <strong>edit / image-to-image</strong> mode;
otherwise runs in <strong>text-to-image</strong> mode.`,name:"image"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.height",description:"<strong>height</strong> &#x2014; Output resolution (height). Defaults to <code>default_sample_size * vae_scale_factor</code> (1024).",name:"height"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.width",description:"<strong>width</strong> &#x2014; Output resolution (width). Defaults to <code>default_sample_size * vae_scale_factor</code> (1024).",name:"width"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.num_inference_steps",description:"<strong>num_inference_steps</strong> &#x2014; Number of denoising steps. Defaults to <strong>4</strong> (distilled).",name:"num_inference_steps"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> &#x2014; Accepted for API parity with <a href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipeline">DreamLitePipeline</a>; <strong>ignored</strong>
because CFG was distilled away.`,name:"guidance_scale"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.image_guidance_scale",description:`<strong>image_guidance_scale</strong> &#x2014; Accepted for API parity with <a href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipeline">DreamLitePipeline</a>; <strong>ignored</strong>
because CFG was distilled away.`,name:"image_guidance_scale"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.sigmas",description:"<strong>sigmas</strong> &#x2014; Optional explicit FlowMatch sigmas; defaults to a uniform linspace.",name:"sigmas"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.num_images_per_prompt",description:"<strong>num_images_per_prompt</strong> &#x2014; Output images per prompt (note: <code>batch_size</code> is forced to 1).",name:"num_images_per_prompt"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.generator",description:"<strong>generator</strong> &#x2014; Random generator(s).",name:"generator"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.output_type",description:"<strong>output_type</strong> &#x2014; <code>&quot;pil&quot;</code>, <code>&quot;np&quot;</code>, <code>&quot;pt&quot;</code> or <code>&quot;latent&quot;</code>.",name:"output_type"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.return_dict",description:'<strong>return_dict</strong> &#x2014; If True, returns a <a href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipelineOutput">DreamLitePipelineOutput</a>; else <code>(images,)</code>.',name:"return_dict"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.max_sequence_length",description:`<strong>max_sequence_length</strong> &#x2014; Maximum number of user-prompt tokens kept after dropping the chat-template
prefix. Only applies to <code>generate</code> mode (the <code>edit</code> mode uses the multimodal processor&#x2019;s native
padding).`,name:"max_sequence_length"},{anchor:"diffusers.DreamLiteMobilePipeline.__call__.text_pad_embedding",description:"<strong>text_pad_embedding</strong> &#x2014; Optional learned pad embedding for masked positions.",name:"text_pad_embedding"}],source:"https://github.com/huggingface/diffusers/blob/vr_13896/src/diffusers/pipelines/dreamlite/pipeline_dreamlite_mobile.py#L384",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p><a
  href="/docs/diffusers/pr_13896/en/api/pipelines/dreamlite#diffusers.DreamLitePipelineOutput"
>DreamLitePipelineOutput</a> or <code>tuple</code>.</p>
`}}),K=new J({props:{title:"DreamLitePipelineOutput",local:"diffusers.DreamLitePipelineOutput",headingTag:"h2"}}),ee=new ye({props:{name:"class diffusers.DreamLitePipelineOutput",anchor:"diffusers.DreamLitePipelineOutput",parameters:[{name:"images",val:": typing.Union[typing.List[PIL.Image.Image], numpy.ndarray]"}],parametersDescription:[{anchor:"diffusers.DreamLitePipelineOutput.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_13896/src/diffusers/pipelines/dreamlite/pipeline_output.py#L25"}}),te=new Yt({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/dreamlite.md"}}),{c(){b=r("meta"),be=n(),_e=r("p"),we=n(),d(I.$$.fragment),Te=n(),d($.$$.fragment),Je=n(),j=r("p"),j.innerHTML=Mt,ve=n(),D=r("p"),D.textContent=yt,Le=n(),Z=r("table"),Z.innerHTML=bt,xe=n(),P=r("p"),P.textContent=wt,Ue=n(),C=r("ul"),C.innerHTML=Tt,Ie=n(),v=r("blockquote"),v.innerHTML=Jt,$e=n(),L=r("blockquote"),L.innerHTML=vt,je=n(),d(G.$$.fragment),De=n(),d(W.$$.fragment),Ze=n(),d(k.$$.fragment),Pe=n(),N=r("p"),N.innerHTML=Lt,Ce=n(),d(E.$$.fragment),Ge=n(),d(q.$$.fragment),We=n(),B=r("p"),B.innerHTML=xt,ke=n(),d(V.$$.fragment),Ne=n(),d(H.$$.fragment),Ee=n(),d(R.$$.fragment),qe=n(),d(Q.$$.fragment),Be=n(),z=r("ul"),z.innerHTML=Ut,Ve=n(),d(F.$$.fragment),He=n(),_=r("div"),d(X.$$.fragment),tt=n(),ne=r("p"),ne.textContent=It,it=n(),ae=r("p"),ae.textContent=$t,nt=n(),se=r("ul"),se.innerHTML=jt,at=n(),le=r("p"),le.innerHTML=Dt,st=n(),re=r("p"),re.innerHTML=Zt,lt=n(),x=r("div"),d(Y.$$.fragment),rt=n(),oe=r("p"),oe.textContent=Pt,Re=n(),d(S.$$.fragment),Qe=n(),m=r("div"),d(A.$$.fragment),ot=n(),pe=r("p"),pe.innerHTML=Ct,pt=n(),me=r("p"),me.textContent=Gt,mt=n(),de=r("ul"),de.innerHTML=Wt,dt=n(),ce=r("p"),ce.innerHTML=kt,ct=n(),ue=r("p"),ue.innerHTML=Nt,ut=n(),ge=r("p"),ge.innerHTML=Et,gt=n(),U=r("div"),d(O.$$.fragment),ft=n(),fe=r("p"),fe.textContent=qt,ze=n(),d(K.$$.fragment),Fe=n(),w=r("div"),d(ee.$$.fragment),ht=n(),he=r("p"),he.textContent=Bt,Xe=n(),d(te.$$.fragment),Ye=n(),Me=r("p"),this.h()},l(e){const t=Ft("svelte-u9bgzb",document.head);b=o(t,"META",{name:!0,content:!0}),t.forEach(i),be=a(e),_e=o(e,"P",{}),ie(_e).forEach(i),we=a(e),c(I.$$.fragment,e),Te=a(e),c($.$$.fragment,e),Je=a(e),j=o(e,"P",{"data-svelte-h":!0}),p(j)!=="svelte-1cvdty3"&&(j.innerHTML=Mt),ve=a(e),D=o(e,"P",{"data-svelte-h":!0}),p(D)!=="svelte-eqvlqp"&&(D.textContent=yt),Le=a(e),Z=o(e,"TABLE",{"data-svelte-h":!0}),p(Z)!=="svelte-1b3g7en"&&(Z.innerHTML=bt),xe=a(e),P=o(e,"P",{"data-svelte-h":!0}),p(P)!=="svelte-rzj34c"&&(P.textContent=wt),Ue=a(e),C=o(e,"UL",{"data-svelte-h":!0}),p(C)!=="svelte-1mekdt9"&&(C.innerHTML=Tt),Ie=a(e),v=o(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),p(v)!=="svelte-8ggazo"&&(v.innerHTML=Jt),$e=a(e),L=o(e,"BLOCKQUOTE",{class:!0,"data-svelte-h":!0}),p(L)!=="svelte-lkkhg9"&&(L.innerHTML=vt),je=a(e),c(G.$$.fragment,e),De=a(e),c(W.$$.fragment,e),Ze=a(e),c(k.$$.fragment,e),Pe=a(e),N=o(e,"P",{"data-svelte-h":!0}),p(N)!=="svelte-muobw2"&&(N.innerHTML=Lt),Ce=a(e),c(E.$$.fragment,e),Ge=a(e),c(q.$$.fragment,e),We=a(e),B=o(e,"P",{"data-svelte-h":!0}),p(B)!=="svelte-zjgokj"&&(B.innerHTML=xt),ke=a(e),c(V.$$.fragment,e),Ne=a(e),c(H.$$.fragment,e),Ee=a(e),c(R.$$.fragment,e),qe=a(e),c(Q.$$.fragment,e),Be=a(e),z=o(e,"UL",{"data-svelte-h":!0}),p(z)!=="svelte-1qxmzhr"&&(z.innerHTML=Ut),Ve=a(e),c(F.$$.fragment,e),He=a(e),_=o(e,"DIV",{class:!0});var y=ie(_);c(X.$$.fragment,y),tt=a(y),ne=o(y,"P",{"data-svelte-h":!0}),p(ne)!=="svelte-1v49ov5"&&(ne.textContent=It),it=a(y),ae=o(y,"P",{"data-svelte-h":!0}),p(ae)!=="svelte-4k4t1y"&&(ae.textContent=$t),nt=a(y),se=o(y,"UL",{"data-svelte-h":!0}),p(se)!=="svelte-107nx4t"&&(se.innerHTML=jt),at=a(y),le=o(y,"P",{"data-svelte-h":!0}),p(le)!=="svelte-cv4flm"&&(le.innerHTML=Dt),st=a(y),re=o(y,"P",{"data-svelte-h":!0}),p(re)!=="svelte-g94rx"&&(re.innerHTML=Zt),lt=a(y),x=o(y,"DIV",{class:!0});var Ae=ie(x);c(Y.$$.fragment,Ae),rt=a(Ae),oe=o(Ae,"P",{"data-svelte-h":!0}),p(oe)!=="svelte-1875ccp"&&(oe.textContent=Pt),Ae.forEach(i),y.forEach(i),Re=a(e),c(S.$$.fragment,e),Qe=a(e),m=o(e,"DIV",{class:!0});var M=ie(m);c(A.$$.fragment,M),ot=a(M),pe=o(M,"P",{"data-svelte-h":!0}),p(pe)!=="svelte-q28wa"&&(pe.innerHTML=Ct),pt=a(M),me=o(M,"P",{"data-svelte-h":!0}),p(me)!=="svelte-1rohv75"&&(me.textContent=Gt),mt=a(M),de=o(M,"UL",{"data-svelte-h":!0}),p(de)!=="svelte-f3dvfk"&&(de.innerHTML=Wt),dt=a(M),ce=o(M,"P",{"data-svelte-h":!0}),p(ce)!=="svelte-1cvaxkj"&&(ce.innerHTML=kt),ct=a(M),ue=o(M,"P",{"data-svelte-h":!0}),p(ue)!=="svelte-keo1ih"&&(ue.innerHTML=Nt),ut=a(M),ge=o(M,"P",{"data-svelte-h":!0}),p(ge)!=="svelte-g94rx"&&(ge.innerHTML=Et),gt=a(M),U=o(M,"DIV",{class:!0});var Oe=ie(U);c(O.$$.fragment,Oe),ft=a(Oe),fe=o(Oe,"P",{"data-svelte-h":!0}),p(fe)!=="svelte-2d3i3l"&&(fe.textContent=qt),Oe.forEach(i),M.forEach(i),ze=a(e),c(K.$$.fragment,e),Fe=a(e),w=o(e,"DIV",{class:!0});var Ke=ie(w);c(ee.$$.fragment,Ke),ht=a(Ke),he=o(Ke,"P",{"data-svelte-h":!0}),p(he)!=="svelte-1sh83xw"&&(he.textContent=Bt),Ke.forEach(i),Xe=a(e),c(te.$$.fragment,e),Ye=a(e),Me=o(e,"P",{}),ie(Me).forEach(i),this.h()},h(){T(b,"name","hf:doc:metadata"),T(b,"content",At),T(v,"class","tip"),T(L,"class","tip"),T(x,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(_,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(U,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(m,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),T(w,"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,t){l(document.head,b),s(e,be,t),s(e,_e,t),s(e,we,t),u(I,e,t),s(e,Te,t),u($,e,t),s(e,Je,t),s(e,j,t),s(e,ve,t),s(e,D,t),s(e,Le,t),s(e,Z,t),s(e,xe,t),s(e,P,t),s(e,Ue,t),s(e,C,t),s(e,Ie,t),s(e,v,t),s(e,$e,t),s(e,L,t),s(e,je,t),u(G,e,t),s(e,De,t),u(W,e,t),s(e,Ze,t),u(k,e,t),s(e,Pe,t),s(e,N,t),s(e,Ce,t),u(E,e,t),s(e,Ge,t),u(q,e,t),s(e,We,t),s(e,B,t),s(e,ke,t),u(V,e,t),s(e,Ne,t),u(H,e,t),s(e,Ee,t),u(R,e,t),s(e,qe,t),u(Q,e,t),s(e,Be,t),s(e,z,t),s(e,Ve,t),u(F,e,t),s(e,He,t),s(e,_,t),u(X,_,null),l(_,tt),l(_,ne),l(_,it),l(_,ae),l(_,nt),l(_,se),l(_,at),l(_,le),l(_,st),l(_,re),l(_,lt),l(_,x),u(Y,x,null),l(x,rt),l(x,oe),s(e,Re,t),u(S,e,t),s(e,Qe,t),s(e,m,t),u(A,m,null),l(m,ot),l(m,pe),l(m,pt),l(m,me),l(m,mt),l(m,de),l(m,dt),l(m,ce),l(m,ct),l(m,ue),l(m,ut),l(m,ge),l(m,gt),l(m,U),u(O,U,null),l(U,ft),l(U,fe),s(e,ze,t),u(K,e,t),s(e,Fe,t),s(e,w,t),u(ee,w,null),l(w,ht),l(w,he),s(e,Xe,t),u(te,e,t),s(e,Ye,t),s(e,Me,t),Se=!0},p:Ht,i(e){Se||(g(I.$$.fragment,e),g($.$$.fragment,e),g(G.$$.fragment,e),g(W.$$.fragment,e),g(k.$$.fragment,e),g(E.$$.fragment,e),g(q.$$.fragment,e),g(V.$$.fragment,e),g(H.$$.fragment,e),g(R.$$.fragment,e),g(Q.$$.fragment,e),g(F.$$.fragment,e),g(X.$$.fragment,e),g(Y.$$.fragment,e),g(S.$$.fragment,e),g(A.$$.fragment,e),g(O.$$.fragment,e),g(K.$$.fragment,e),g(ee.$$.fragment,e),g(te.$$.fragment,e),Se=!0)},o(e){f(I.$$.fragment,e),f($.$$.fragment,e),f(G.$$.fragment,e),f(W.$$.fragment,e),f(k.$$.fragment,e),f(E.$$.fragment,e),f(q.$$.fragment,e),f(V.$$.fragment,e),f(H.$$.fragment,e),f(R.$$.fragment,e),f(Q.$$.fragment,e),f(F.$$.fragment,e),f(X.$$.fragment,e),f(Y.$$.fragment,e),f(S.$$.fragment,e),f(A.$$.fragment,e),f(O.$$.fragment,e),f(K.$$.fragment,e),f(ee.$$.fragment,e),f(te.$$.fragment,e),Se=!1},d(e){e&&(i(be),i(_e),i(we),i(Te),i(Je),i(j),i(ve),i(D),i(Le),i(Z),i(xe),i(P),i(Ue),i(C),i(Ie),i(v),i($e),i(L),i(je),i(De),i(Ze),i(Pe),i(N),i(Ce),i(Ge),i(We),i(B),i(ke),i(Ne),i(Ee),i(qe),i(Be),i(z),i(Ve),i(He),i(_),i(Re),i(Qe),i(m),i(ze),i(Fe),i(w),i(Xe),i(Ye),i(Me)),i(b),h(I,e),h($,e),h(G,e),h(W,e),h(k,e),h(E,e),h(q,e),h(V,e),h(H,e),h(R,e),h(Q,e),h(F,e),h(X),h(Y),h(S,e),h(A),h(O),h(K,e),h(ee),h(te,e)}}}const At='{"title":"DreamLite","local":"dreamlite","sections":[{"title":"Text-to-image (Base)","local":"text-to-image-base","sections":[],"depth":2},{"title":"Image editing (Base)","local":"image-editing-base","sections":[],"depth":2},{"title":"Text-to-image (Mobile)","local":"text-to-image-mobile","sections":[],"depth":2},{"title":"Image editing (Mobile)","local":"image-editing-mobile","sections":[],"depth":2},{"title":"Notes and limitations","local":"notes-and-limitations","sections":[],"depth":2},{"title":"DreamLitePipeline","local":"diffusers.DreamLitePipeline","sections":[],"depth":2},{"title":"DreamLiteMobilePipeline","local":"diffusers.DreamLiteMobilePipeline","sections":[],"depth":2},{"title":"DreamLitePipelineOutput","local":"diffusers.DreamLitePipelineOutput","sections":[],"depth":2}],"depth":1}';function Ot(_t){return Rt(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class si extends Qt{constructor(b){super(),zt(this,b,Ot,St,Vt,{})}}export{si as component};