diffusers/pr_13860/en/_app/immutable/nodes/161.9e9b3d22.js

import{s as nt,o as at,n as ot}from"../chunks/scheduler.53228c21.js";import{S as rt,i as st,e as i,s as a,c as u,h as it,a as l,d as n,b as o,f as J,g,j as f,k as C,l as r,m as s,n as h,t as _,o as v,p as b}from"../chunks/index.cac5d66a.js";import{C as lt}from"../chunks/CopyLLMTxtMenu.94f1b9f3.js";import{D as le}from"../chunks/Docstring.ad6457df.js";import{C as tt}from"../chunks/CodeBlock.606cbaf4.js";import{E as dt}from"../chunks/ExampleCodeBlock.1a02521d.js";import{H as Ie,E as pt}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.fff5b5d9.js";function mt(pe){let m,U="Examples:",$,y,x;return y=new tt({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> Ideogram4Pipeline

<span class="hljs-meta">&gt;&gt;&gt; </span>pipe = Ideogram4Pipeline.from_pretrained(<span class="hljs-string">&quot;ideogram-ai/ideogram-v4&quot;</span>, torch_dtype=torch.bfloat16)
<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 photo of a cat holding a sign that says hello world&quot;</span>
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># The defaults are the recommended settings for best quality.</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>image = pipe(prompt, height=<span class="hljs-number">2048</span>, width=<span class="hljs-number">2048</span>, generator=torch.Generator(<span class="hljs-string">&quot;cuda&quot;</span>).manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>]
<span class="hljs-meta">&gt;&gt;&gt; </span>image.save(<span class="hljs-string">&quot;ideogram4.png&quot;</span>)`,lang:"py",wrap:!1}}),{c(){m=i("p"),m.textContent=U,$=a(),u(y.$$.fragment)},l(d){m=l(d,"P",{"data-svelte-h":!0}),f(m)!=="svelte-kvfsh7"&&(m.textContent=U),$=o(d),g(y.$$.fragment,d)},m(d,w){s(d,m,w),s(d,$,w),h(y,d,w),x=!0},p:ot,i(d){x||(_(y.$$.fragment,d),x=!0)},o(d){v(y.$$.fragment,d),x=!1},d(d){d&&(n(m),n($)),b(y,d)}}}function ct(pe){let m,U,$,y,x,d,w,me,G,He=`Ideogram 4 is a flow-matching text-to-image model that uses a multimodal text encoder and an asymmetric
classifier-free guidance scheme: a dedicated <code>unconditional_transformer</code> produces the negative branch with zeroed text
features, while the main <code>transformer</code> consumes the full packed text + image sequence.`,ce,W,Re=`The pipeline defaults are the recommended settings for best quality, so a plain <code>pipe(prompt)</code> call produces
best-quality results out of the box: 48 flow-matching steps on a logit-normal schedule (<code>mu=0.0</code>, <code>std=1.5</code>) with
classifier-free guidance held at 7.0 for the main steps and dropped to 3.0 for the final 3 “polish” steps.`,ue,E,Se="Key inference-time knobs are exposed via the pipeline call:",ge,q,Fe="<li><code>num_inference_steps</code>, <code>mu</code>, and <code>std</code> control the resolution-aware logit-normal flow-matching schedule.</li> <li><code>guidance_scale</code> (or a full per-step <code>guidance_schedule</code>) blends the conditional and unconditional velocities.</li>",fe,N,he,Z,_e,L,ve,p,V,Te,D,ze="Text-to-image pipeline for Ideogram4.",je,O,Be=`Ideogram4 is a flow-matching model trained with asymmetric classifier-free guidance: a <code>transformer</code> consumes
text-conditioned features alongside the image latents, while a separate <code>unconditional_transformer</code> denoises with
zeroed text features. The two velocity predictions are linearly blended each step.`,Pe,M,H,ke,A,Ye="Run text-to-image generation.",Je,k,Ce,I,R,Ue,Q,De="Prepare the conditioning for the packed text+image sequence (one entry per prompt).",Ge,X,Oe=`Returns a flat tuple <code>(prompt_embeds, position_ids, segment_ids, indicator)</code>. The unconditional branch carries
no text, so the pipeline builds its (zeroed) inputs directly rather than encoding a negative prompt.`,We,T,S,Ee,K,Ae="Make the frozen text encoder generative for prompt upsampling by grafting a hosted LM head.",qe,ee,Qe=`The head is the only extra weight loaded; the encoder body is shared (no second model in memory).
Called automatically by <code>upsample_prompt</code> on first use. Generation is constrained to the caption JSON
schema when <code>outlines</code> is installed; otherwise it falls back to unconstrained decoding with a warning.`,Ne,j,F,Ze,te,Xe="Rewrite each prompt into Ideogram4’s native structured JSON caption via the grafted text encoder.",Le,ne,Ke="Pass <code>generator</code> (the same one accepted by <code>__call__</code>) to make sampling reproducible.",be,z,ye,P,B,Ve,ae,et="Output class for the Ideogram 4 pipeline.",xe,Y,we,de,$e;return x=new lt({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),w=new Ie({props:{title:"Ideogram 4",local:"ideogram-4",headingTag:"h1"}}),N=new Ie({props:{title:"Text-to-image",local:"text-to-image",headingTag:"h2"}}),Z=new tt({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> Ideogram4Pipeline

pipe = Ideogram4Pipeline.from_pretrained(<span class="hljs-string">&quot;ideogram-ai/ideogram-v4&quot;</span>, torch_dtype=torch.bfloat16)
pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

prompt = <span class="hljs-string">&quot;A photo of a cat holding a sign that says hello world&quot;</span>
<span class="hljs-comment"># The defaults are the recommended settings for best quality.</span>
image = pipe(prompt, height=<span class="hljs-number">1024</span>, width=<span class="hljs-number">1024</span>, generator=torch.Generator(<span class="hljs-string">&quot;cuda&quot;</span>).manual_seed(<span class="hljs-number">0</span>)).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">&quot;ideogram4.png&quot;</span>)`,lang:"python",wrap:!1}}),L=new Ie({props:{title:"Ideogram4Pipeline",local:"diffusers.Ideogram4Pipeline",headingTag:"h2"}}),V=new le({props:{name:"class diffusers.Ideogram4Pipeline",anchor:"diffusers.Ideogram4Pipeline",parameters:[{name:"scheduler",val:": FlowMatchEulerDiscreteScheduler"},{name:"vae",val:": AutoencoderKLFlux2"},{name:"text_encoder",val:": PreTrainedModel"},{name:"tokenizer",val:": AutoTokenizer"},{name:"transformer",val:": Ideogram4Transformer2DModel"},{name:"unconditional_transformer",val:": Ideogram4Transformer2DModel"},{name:"prompt_enhancer",val:": transformers.modeling_utils.PreTrainedModel | None = None"}],parametersDescription:[{anchor:"diffusers.Ideogram4Pipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/pr_13860/en/api/schedulers/flow_match_euler_discrete#diffusers.FlowMatchEulerDiscreteScheduler">FlowMatchEulerDiscreteScheduler</a>) &#x2014;
Flow-matching scheduler. The pipeline overrides the default sigma schedule with a resolution-aware
logit-normal schedule.`,name:"scheduler"},{anchor:"diffusers.Ideogram4Pipeline.vae",description:`<strong>vae</strong> (<code>AutoencoderKLFlux2</code>) &#x2014;
Variational auto-encoder used to decode latents back into images.`,name:"vae"},{anchor:"diffusers.Ideogram4Pipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>PreTrainedModel</code>) &#x2014;
Multimodal text encoder. The pipeline consumes hidden states from a fixed set of intermediate decoder
layers (see <code>QWEN3_VL_ACTIVATION_LAYERS</code>).`,name:"text_encoder"},{anchor:"diffusers.Ideogram4Pipeline.tokenizer",description:`<strong>tokenizer</strong> (<code>AutoTokenizer</code>) &#x2014;
Tokenizer paired with <code>text_encoder</code>.`,name:"tokenizer"},{anchor:"diffusers.Ideogram4Pipeline.transformer",description:`<strong>transformer</strong> (<a href="/docs/diffusers/pr_13860/en/api/models/ideogram4_transformer2d#diffusers.Ideogram4Transformer2DModel">Ideogram4Transformer2DModel</a>) &#x2014;
Conditional flow-matching transformer.`,name:"transformer"},{anchor:"diffusers.Ideogram4Pipeline.unconditional_transformer",description:`<strong>unconditional_transformer</strong> (<a href="/docs/diffusers/pr_13860/en/api/models/ideogram4_transformer2d#diffusers.Ideogram4Transformer2DModel">Ideogram4Transformer2DModel</a>) &#x2014;
Unconditional (asymmetric-CFG) flow-matching transformer.`,name:"unconditional_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_13860/src/diffusers/pipelines/ideogram4/pipeline_ideogram4.py#L139"}}),H=new le({props:{name:"__call__",anchor:"diffusers.Ideogram4Pipeline.__call__",parameters:[{name:"prompt",val:": str | list[str] | None = None"},{name:"height",val:": int = 2048"},{name:"width",val:": int = 2048"},{name:"num_inference_steps",val:": int = 48"},{name:"guidance_scale",val:": float | None = None"},{name:"guidance_schedule",val:": list[float] | torch.Tensor | None = (7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 7.0, 3.0, 3.0, 3.0)"},{name:"mu",val:": float = 0.0"},{name:"std",val:": float = 1.5"},{name:"prompt_upsampling",val:": bool = False"},{name:"prompt_upsampling_temperature",val:": float = 1.0"},{name:"max_sequence_length",val:": int = 2048"},{name:"num_images_per_prompt",val:": int = 1"},{name:"generator",val:": torch._C.Generator | list[torch._C.Generator] | None = None"},{name:"latents",val:": torch.Tensor | None = None"},{name:"output_type",val:": str = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"callback_on_step_end",val:": typing.Optional[typing.Callable[[ForwardRef('Ideogram4Pipeline'), int, int, dict[str, typing.Any]], dict[str, typing.Any]]] = None"},{name:"callback_on_step_end_tensor_inputs",val:": list = ['latents']"}],parametersDescription:[{anchor:"diffusers.Ideogram4Pipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>list[str]</code>) &#x2014;
Prompt(s) to guide image generation.`,name:"prompt"},{anchor:"diffusers.Ideogram4Pipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to 2048) &#x2014;
Output image height in pixels; must be a multiple of <code>vae_scale_factor * patch_size</code>.`,name:"height"},{anchor:"diffusers.Ideogram4Pipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to 2048) &#x2014;
Output image width in pixels; must be a multiple of <code>vae_scale_factor * patch_size</code>.`,name:"width"},{anchor:"diffusers.Ideogram4Pipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 48) &#x2014;
Number of flow-matching steps. The default is the recommended setting for best quality.`,name:"num_inference_steps"},{anchor:"diffusers.Ideogram4Pipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>) &#x2014;
Constant classifier-free guidance scale applied at every step. The conditional and unconditional
velocity predictions are blended as <code>v = guidance_scale * v_pos + (1 - guidance_scale) * v_neg</code>.
Mutually exclusive with <code>guidance_schedule</code> (setting both raises). Defaults to <code>None</code>.`,name:"guidance_scale"},{anchor:"diffusers.Ideogram4Pipeline.__call__.guidance_schedule",description:`<strong>guidance_schedule</strong> (<code>list[float]</code> or <code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Per-step guidance scale schedule; must have length <code>num_inference_steps</code>. The first entry corresponds
to the first step (largest noise level). Mutually exclusive with <code>guidance_scale</code>; exactly one must be
set. Defaults to the recommended schedule (7.0 for the main steps, dropping to 3.0 for the final 3
&#x201C;polish&#x201D; steps). To use a constant scale instead, pass <code>guidance_scale</code> and <code>guidance_schedule=None</code>.`,name:"guidance_schedule"},{anchor:"diffusers.Ideogram4Pipeline.__call__.mu",description:`<strong>mu</strong> (<code>float</code>, <em>optional</em>, defaults to 0.0) &#x2014;
Base mean of the logit-normal flow-matching schedule. The schedule mean is shifted by half the log of
the resolution ratio relative to 512x512.`,name:"mu"},{anchor:"diffusers.Ideogram4Pipeline.__call__.std",description:`<strong>std</strong> (<code>float</code>, <em>optional</em>, defaults to 1.5) &#x2014;
Standard deviation of the logit-normal flow-matching schedule.`,name:"std"},{anchor:"diffusers.Ideogram4Pipeline.__call__.prompt_upsampling",description:`<strong>prompt_upsampling</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
If <code>True</code>, rewrite <code>prompt</code> into Ideogram4&#x2019;s native structured JSON caption via
<a href="/docs/diffusers/pr_13860/en/api/pipelines/ideogram4#diffusers.Ideogram4Pipeline.upsample_prompt">upsample_prompt()</a> before encoding. Requires the prompt-enhancer LM head
(downloaded on first use); install <code>outlines</code> for schema-constrained captions. <code>generator</code> is
reused to make the upsampling reproducible.`,name:"prompt_upsampling"},{anchor:"diffusers.Ideogram4Pipeline.__call__.prompt_upsampling_temperature",description:`<strong>prompt_upsampling_temperature</strong> (<code>float</code>, <em>optional</em>, defaults to 1.0) &#x2014;
Sampling temperature for prompt upsampling when <code>prompt_upsampling=True</code>.`,name:"prompt_upsampling_temperature"},{anchor:"diffusers.Ideogram4Pipeline.__call__.max_sequence_length",description:`<strong>max_sequence_length</strong> (<code>int</code>, <em>optional</em>, defaults to 2048) &#x2014;
Maximum number of text tokens per prompt.`,name:"max_sequence_length"},{anchor:"diffusers.Ideogram4Pipeline.__call__.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) &#x2014;
Number of images to generate per prompt.`,name:"num_images_per_prompt"},{anchor:"diffusers.Ideogram4Pipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code> or <code>list[torch.Generator]</code>, <em>optional</em>) &#x2014;
Generator(s) used to make sampling deterministic.`,name:"generator"},{anchor:"diffusers.Ideogram4Pipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated noise of shape <code>(batch_size, num_image_tokens, latent_dim)</code>.`,name:"latents"},{anchor:"diffusers.Ideogram4Pipeline.__call__.output_type",description:`<strong>output_type</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;pil&quot;</code>) &#x2014;
One of <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.Ideogram4Pipeline.__call__.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to return an <a href="/docs/diffusers/pr_13860/en/api/pipelines/ideogram4#diffusers.pipelines.ideogram4.Ideogram4PipelineOutput">Ideogram4PipelineOutput</a>.`,name:"return_dict"},{anchor:"diffusers.Ideogram4Pipeline.__call__.callback_on_step_end",description:`<strong>callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) &#x2014;
Callback invoked at the end of every denoising step.`,name:"callback_on_step_end"},{anchor:"diffusers.Ideogram4Pipeline.__call__.callback_on_step_end_tensor_inputs",description:`<strong>callback_on_step_end_tensor_inputs</strong> (<code>list[str]</code>, <em>optional</em>) &#x2014;
Names of tensors to expose to the callback via <code>callback_kwargs</code>.`,name:"callback_on_step_end_tensor_inputs"}],source:"https://github.com/huggingface/diffusers/blob/vr_13860/src/diffusers/pipelines/ideogram4/pipeline_ideogram4.py#L467",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


<p><a
  href="/docs/diffusers/pr_13860/en/api/pipelines/ideogram4#diffusers.pipelines.ideogram4.Ideogram4PipelineOutput"
>Ideogram4PipelineOutput</a> or <code>tuple</code>.</p>
`}}),k=new dt({props:{anchor:"diffusers.Ideogram4Pipeline.__call__.example",$$slots:{default:[mt]},$$scope:{ctx:pe}}}),R=new le({props:{name:"encode_prompt",anchor:"diffusers.Ideogram4Pipeline.encode_prompt",parameters:[{name:"prompt",val:": str | list[str]"},{name:"grid_h",val:": int"},{name:"grid_w",val:": int"},{name:"max_sequence_length",val:": int"},{name:"device",val:": device"}],source:"https://github.com/huggingface/diffusers/blob/vr_13860/src/diffusers/pipelines/ideogram4/pipeline_ideogram4.py#L333"}}),S=new le({props:{name:"load_prompt_enhancer",anchor:"diffusers.Ideogram4Pipeline.load_prompt_enhancer",parameters:[{name:"lm_head_repo_id",val:": str = 'diffusers/qwen3-vl-8b-instruct-lm-head'"},{name:"lm_head_filename",val:": str = 'lm_head.safetensors'"},{name:"torch_dtype",val:": torch.dtype | None = None"}],source:"https://github.com/huggingface/diffusers/blob/vr_13860/src/diffusers/pipelines/ideogram4/pipeline_ideogram4.py#L200"}}),F=new le({props:{name:"upsample_prompt",anchor:"diffusers.Ideogram4Pipeline.upsample_prompt",parameters:[{name:"prompt",val:": str | list[str]"},{name:"height",val:": int = 2048"},{name:"width",val:": int = 2048"},{name:"temperature",val:": float = 1.0"},{name:"max_new_tokens",val:": int = 1024"},{name:"generator",val:": torch._C.Generator | list[torch._C.Generator] | None = None"},{name:"lm_head_repo_id",val:": str = 'diffusers/qwen3-vl-8b-instruct-lm-head'"},{name:"device",val:": torch.device | None = None"}],source:"https://github.com/huggingface/diffusers/blob/vr_13860/src/diffusers/pipelines/ideogram4/pipeline_ideogram4.py#L218"}}),z=new Ie({props:{title:"Ideogram4PipelineOutput",local:"diffusers.pipelines.ideogram4.Ideogram4PipelineOutput",headingTag:"h2"}}),B=new le({props:{name:"class diffusers.pipelines.ideogram4.Ideogram4PipelineOutput",anchor:"diffusers.pipelines.ideogram4.Ideogram4PipelineOutput",parameters:[{name:"images",val:": list[PIL.Image.Image] | numpy.ndarray"}],parametersDescription:[{anchor:"diffusers.pipelines.ideogram4.Ideogram4PipelineOutput.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>.`,name:"images"}],source:"https://github.com/huggingface/diffusers/blob/vr_13860/src/diffusers/pipelines/ideogram4/pipeline_output.py#L24"}}),Y=new pt({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/ideogram4.md"}}),{c(){m=i("meta"),U=a(),$=i("p"),y=a(),u(x.$$.fragment),d=a(),u(w.$$.fragment),me=a(),G=i("p"),G.innerHTML=He,ce=a(),W=i("p"),W.innerHTML=Re,ue=a(),E=i("p"),E.textContent=Se,ge=a(),q=i("ul"),q.innerHTML=Fe,fe=a(),u(N.$$.fragment),he=a(),u(Z.$$.fragment),_e=a(),u(L.$$.fragment),ve=a(),p=i("div"),u(V.$$.fragment),Te=a(),D=i("p"),D.textContent=ze,je=a(),O=i("p"),O.innerHTML=Be,Pe=a(),M=i("div"),u(H.$$.fragment),ke=a(),A=i("p"),A.textContent=Ye,Je=a(),u(k.$$.fragment),Ce=a(),I=i("div"),u(R.$$.fragment),Ue=a(),Q=i("p"),Q.textContent=De,Ge=a(),X=i("p"),X.innerHTML=Oe,We=a(),T=i("div"),u(S.$$.fragment),Ee=a(),K=i("p"),K.textContent=Ae,qe=a(),ee=i("p"),ee.innerHTML=Qe,Ne=a(),j=i("div"),u(F.$$.fragment),Ze=a(),te=i("p"),te.textContent=Xe,Le=a(),ne=i("p"),ne.innerHTML=Ke,be=a(),u(z.$$.fragment),ye=a(),P=i("div"),u(B.$$.fragment),Ve=a(),ae=i("p"),ae.textContent=et,xe=a(),u(Y.$$.fragment),we=a(),de=i("p"),this.h()},l(e){const t=it("svelte-u9bgzb",document.head);m=l(t,"META",{name:!0,content:!0}),t.forEach(n),U=o(e),$=l(e,"P",{}),J($).forEach(n),y=o(e),g(x.$$.fragment,e),d=o(e),g(w.$$.fragment,e),me=o(e),G=l(e,"P",{"data-svelte-h":!0}),f(G)!=="svelte-z8pr89"&&(G.innerHTML=He),ce=o(e),W=l(e,"P",{"data-svelte-h":!0}),f(W)!=="svelte-xco4w2"&&(W.innerHTML=Re),ue=o(e),E=l(e,"P",{"data-svelte-h":!0}),f(E)!=="svelte-gyrac2"&&(E.textContent=Se),ge=o(e),q=l(e,"UL",{"data-svelte-h":!0}),f(q)!=="svelte-1s1ga53"&&(q.innerHTML=Fe),fe=o(e),g(N.$$.fragment,e),he=o(e),g(Z.$$.fragment,e),_e=o(e),g(L.$$.fragment,e),ve=o(e),p=l(e,"DIV",{class:!0});var c=J(p);g(V.$$.fragment,c),Te=o(c),D=l(c,"P",{"data-svelte-h":!0}),f(D)!=="svelte-ysojjo"&&(D.textContent=ze),je=o(c),O=l(c,"P",{"data-svelte-h":!0}),f(O)!=="svelte-1jolije"&&(O.innerHTML=Be),Pe=o(c),M=l(c,"DIV",{class:!0});var oe=J(M);g(H.$$.fragment,oe),ke=o(oe),A=l(oe,"P",{"data-svelte-h":!0}),f(A)!=="svelte-1n34az2"&&(A.textContent=Ye),Je=o(oe),g(k.$$.fragment,oe),oe.forEach(n),Ce=o(c),I=l(c,"DIV",{class:!0});var re=J(I);g(R.$$.fragment,re),Ue=o(re),Q=l(re,"P",{"data-svelte-h":!0}),f(Q)!=="svelte-p737jv"&&(Q.textContent=De),Ge=o(re),X=l(re,"P",{"data-svelte-h":!0}),f(X)!=="svelte-1ymcwo9"&&(X.innerHTML=Oe),re.forEach(n),We=o(c),T=l(c,"DIV",{class:!0});var se=J(T);g(S.$$.fragment,se),Ee=o(se),K=l(se,"P",{"data-svelte-h":!0}),f(K)!=="svelte-jizbsj"&&(K.textContent=Ae),qe=o(se),ee=l(se,"P",{"data-svelte-h":!0}),f(ee)!=="svelte-10oebgl"&&(ee.innerHTML=Qe),se.forEach(n),Ne=o(c),j=l(c,"DIV",{class:!0});var ie=J(j);g(F.$$.fragment,ie),Ze=o(ie),te=l(ie,"P",{"data-svelte-h":!0}),f(te)!=="svelte-1f1ov5g"&&(te.textContent=Xe),Le=o(ie),ne=l(ie,"P",{"data-svelte-h":!0}),f(ne)!=="svelte-1qtsory"&&(ne.innerHTML=Ke),ie.forEach(n),c.forEach(n),be=o(e),g(z.$$.fragment,e),ye=o(e),P=l(e,"DIV",{class:!0});var Me=J(P);g(B.$$.fragment,Me),Ve=o(Me),ae=l(Me,"P",{"data-svelte-h":!0}),f(ae)!=="svelte-5vp3kd"&&(ae.textContent=et),Me.forEach(n),xe=o(e),g(Y.$$.fragment,e),we=o(e),de=l(e,"P",{}),J(de).forEach(n),this.h()},h(){C(m,"name","hf:doc:metadata"),C(m,"content",ut),C(M,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(I,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(j,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(p,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),C(P,"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){r(document.head,m),s(e,U,t),s(e,$,t),s(e,y,t),h(x,e,t),s(e,d,t),h(w,e,t),s(e,me,t),s(e,G,t),s(e,ce,t),s(e,W,t),s(e,ue,t),s(e,E,t),s(e,ge,t),s(e,q,t),s(e,fe,t),h(N,e,t),s(e,he,t),h(Z,e,t),s(e,_e,t),h(L,e,t),s(e,ve,t),s(e,p,t),h(V,p,null),r(p,Te),r(p,D),r(p,je),r(p,O),r(p,Pe),r(p,M),h(H,M,null),r(M,ke),r(M,A),r(M,Je),h(k,M,null),r(p,Ce),r(p,I),h(R,I,null),r(I,Ue),r(I,Q),r(I,Ge),r(I,X),r(p,We),r(p,T),h(S,T,null),r(T,Ee),r(T,K),r(T,qe),r(T,ee),r(p,Ne),r(p,j),h(F,j,null),r(j,Ze),r(j,te),r(j,Le),r(j,ne),s(e,be,t),h(z,e,t),s(e,ye,t),s(e,P,t),h(B,P,null),r(P,Ve),r(P,ae),s(e,xe,t),h(Y,e,t),s(e,we,t),s(e,de,t),$e=!0},p(e,[t]){const c={};t&2&&(c.$$scope={dirty:t,ctx:e}),k.$set(c)},i(e){$e||(_(x.$$.fragment,e),_(w.$$.fragment,e),_(N.$$.fragment,e),_(Z.$$.fragment,e),_(L.$$.fragment,e),_(V.$$.fragment,e),_(H.$$.fragment,e),_(k.$$.fragment,e),_(R.$$.fragment,e),_(S.$$.fragment,e),_(F.$$.fragment,e),_(z.$$.fragment,e),_(B.$$.fragment,e),_(Y.$$.fragment,e),$e=!0)},o(e){v(x.$$.fragment,e),v(w.$$.fragment,e),v(N.$$.fragment,e),v(Z.$$.fragment,e),v(L.$$.fragment,e),v(V.$$.fragment,e),v(H.$$.fragment,e),v(k.$$.fragment,e),v(R.$$.fragment,e),v(S.$$.fragment,e),v(F.$$.fragment,e),v(z.$$.fragment,e),v(B.$$.fragment,e),v(Y.$$.fragment,e),$e=!1},d(e){e&&(n(U),n($),n(y),n(d),n(me),n(G),n(ce),n(W),n(ue),n(E),n(ge),n(q),n(fe),n(he),n(_e),n(ve),n(p),n(be),n(ye),n(P),n(xe),n(we),n(de)),n(m),b(x,e),b(w,e),b(N,e),b(Z,e),b(L,e),b(V),b(H),b(k),b(R),b(S),b(F),b(z,e),b(B),b(Y,e)}}}const ut='{"title":"Ideogram 4","local":"ideogram-4","sections":[{"title":"Text-to-image","local":"text-to-image","sections":[],"depth":2},{"title":"Ideogram4Pipeline","local":"diffusers.Ideogram4Pipeline","sections":[],"depth":2},{"title":"Ideogram4PipelineOutput","local":"diffusers.pipelines.ideogram4.Ideogram4PipelineOutput","sections":[],"depth":2}],"depth":1}';function gt(pe){return at(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class wt extends rt{constructor(m){super(),st(this,m,gt,ct,nt,{})}}export{wt as component};