Buckets:
| import{s as tt,o as nt,n as et}from"../chunks/scheduler.8c3d61f6.js";import{S as ot,i as st,g as l,s,r as m,A as it,h as r,f as n,c as i,j as oe,u,x as M,k as se,y as c,a as o,v as f,d as g,t as h,w as _}from"../chunks/index.da70eac4.js";import{T as at}from"../chunks/Tip.1d9b8c37.js";import{D as Ce}from"../chunks/Docstring.ee4b6913.js";import{C as ae}from"../chunks/CodeBlock.00a903b3.js";import{E as lt}from"../chunks/ExampleCodeBlock.f7bd2c1f.js";import{H as Ge,E as rt}from"../chunks/EditOnGithub.1e64e623.js";function dt(A){let a,v='Make sure to check out the Schedulers <a href="../../using-diffusers/schedulers.md">guide</a> to learn how to explore the tradeoff between scheduler speed and quality, and see the <a href="../../using-diffusers/loading.md#reuse-a-pipeline">reuse components across pipelines</a> section to learn how to efficiently load the same components into multiple pipelines.';return{c(){a=l("p"),a.innerHTML=v},l(p){a=r(p,"P",{"data-svelte-h":!0}),M(a)!=="svelte-w7r39y"&&(a.innerHTML=v)},m(p,w){o(p,a,w)},p:et,d(p){p&&n(a)}}}function pt(A){let a,v="Examples:",p,w,T;return w=new ae({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> CogVideoXPipeline | |
| <span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> export_to_video | |
| <span class="hljs-meta">>>> </span>pipe = CogVideoXPipeline.from_pretrained(<span class="hljs-string">"THUDM/CogVideoX-2b"</span>, torch_dtype=torch.float16).to(<span class="hljs-string">"cuda"</span>) | |
| <span class="hljs-meta">>>> </span>prompt = ( | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. "</span> | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other "</span> | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, "</span> | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. "</span> | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical "</span> | |
| <span class="hljs-meta">... </span> <span class="hljs-string">"atmosphere of this unique musical performance."</span> | |
| <span class="hljs-meta">... </span>) | |
| <span class="hljs-meta">>>> </span>video = pipe(prompt=prompt, guidance_scale=<span class="hljs-number">6</span>, num_inference_steps=<span class="hljs-number">50</span>).frames[<span class="hljs-number">0</span>] | |
| <span class="hljs-meta">>>> </span>export_to_video(video, <span class="hljs-string">"output.mp4"</span>, fps=<span class="hljs-number">8</span>)`,wrap:!1}}),{c(){a=l("p"),a.textContent=v,p=s(),m(w.$$.fragment)},l(d){a=r(d,"P",{"data-svelte-h":!0}),M(a)!=="svelte-kvfsh7"&&(a.textContent=v),p=i(d),u(w.$$.fragment,d)},m(d,J){o(d,a,J),o(d,p,J),f(w,d,J),T=!0},p:et,i(d){T||(g(w.$$.fragment,d),T=!0)},o(d){h(w.$$.fragment,d),T=!1},d(d){d&&(n(a),n(p)),_(w,d)}}}function ct(A){let a,v,p,w,T,d,J,Ne='<a href="https://github.com/THUDM/CogVideo/blob/main/resources/CogVideoX.pdf" rel="nofollow">CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer</a> from Tsinghua University & ZhipuAI.',le,G,Pe="The abstract from the paper is:",re,V,ze='<em>We introduce CogVideoX, a large-scale diffusion transformer model designed for generating videos based on text prompts. To efficently model video data, we propose to levearge a 3D Variational Autoencoder (VAE) to compresses videos along both spatial and temporal dimensions. To improve the text-video alignment, we propose an expert transformer with the expert adaptive LayerNorm to facilitate the deep fusion between the two modalities. By employing a progressive training technique, CogVideoX is adept at producing coherent, long-duration videos characterized by significant motion. In addition, we develop an effectively text-video data processing pipeline that includes various data preprocessing strategies and a video captioning method. It significantly helps enhance the performance of CogVideoX, improving both generation quality and semantic alignment. Results show that CogVideoX demonstrates state-of-the-art performance across both multiple machine metrics and human evaluations. The model weight of CogVideoX-2B is publicly available at <a href="https://github.com/THUDM/CogVideo" rel="nofollow">https://github.com/THUDM/CogVideo</a>.</em>',de,x,pe,B,Fe='This pipeline was contributed by <a href="https://github.com/zRzRzRzRzRzRzR" rel="nofollow">zRzRzRzRzRzRzR</a>. The original codebase can be found <a href="https://huggingface.co/THUDM" rel="nofollow">here</a>. The original weights can be found under <a href="https://huggingface.co/THUDM" rel="nofollow">hf.co/THUDM</a>.',ce,X,me,W,Re='Use <a href="https://huggingface.co/docs/diffusers/main/en/tutorials/fast_diffusion#torchcompile" rel="nofollow"><code>torch.compile</code></a> to reduce the inference latency.',ue,$,Se="First, load the pipeline:",fe,k,ge,H,Qe="Then change the memory layout of the pipelines <code>transformer</code> and <code>vae</code> components to <code>torch.channels-last</code>:",he,Y,_e,N,Ee="Finally, compile the components and run inference:",Me,P,be,z,qe="The [benchmark](TODO: link) results on an 80GB A100 machine are:",we,F,ye,R,Te,b,S,Ve,O,Le="Pipeline for text-to-video generation using CogVideoX.",Be,K,De=`This model inherits from <a href="/docs/diffusers/pr_9017/en/api/pipelines/overview#diffusers.DiffusionPipeline">DiffusionPipeline</a>. Check the superclass documentation for the generic methods the | |
| library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)`,Xe,U,Q,We,ee,Ae="Function invoked when calling the pipeline for generation.",$e,Z,ke,C,E,He,te,Oe="Encodes the prompt into text encoder hidden states.",Je,q,ve,j,L,Ye,ne,Ke="Output class for CogVideo pipelines.",Ue,D,je,ie,Ie;return T=new Ge({props:{title:"CogVideoX",local:"cogvideox",headingTag:"h1"}}),x=new at({props:{$$slots:{default:[dt]},$$scope:{ctx:A}}}),X=new Ge({props:{title:"Inference",local:"inference",headingTag:"h2"}}),k=new ae({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> CogVideoXPipeline | |
| <span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> export_to_video | |
| pipe = CogVideoXPipeline.from_pretrained(<span class="hljs-string">"THUDM/CogVideoX-2b"</span>).to(<span class="hljs-string">"cuda"</span>) | |
| prompt = ( | |
| <span class="hljs-string">"A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. "</span> | |
| <span class="hljs-string">"The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other "</span> | |
| <span class="hljs-string">"pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, "</span> | |
| <span class="hljs-string">"casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. "</span> | |
| <span class="hljs-string">"The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical "</span> | |
| <span class="hljs-string">"atmosphere of this unique musical performance."</span> | |
| ) | |
| video = pipe(prompt=prompt, guidance_scale=<span class="hljs-number">6</span>, num_inference_steps=<span class="hljs-number">50</span>).frames[<span class="hljs-number">0</span>] | |
| export_to_video(video, <span class="hljs-string">"output.mp4"</span>, fps=<span class="hljs-number">8</span>)`,wrap:!1}}),Y=new ae({props:{code:"cGlwZWxpbmUudHJhbnNmb3JtZXIudG8obWVtb3J5X2Zvcm1hdCUzRHRvcmNoLmNoYW5uZWxzX2xhc3QpJTBBcGlwZWxpbmUudmFlLnRvKG1lbW9yeV9mb3JtYXQlM0R0b3JjaC5jaGFubmVsc19sYXN0KQ==",highlighted:`pipeline.transformer.to(memory_format=torch.channels_last) | |
| pipeline.vae.to(memory_format=torch.channels_last)`,wrap:!1}}),P=new ae({props:{code:"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",highlighted:`pipeline.transformer = torch.<span class="hljs-built_in">compile</span>(pipeline.transformer) | |
| pipeline.vae.decode = torch.<span class="hljs-built_in">compile</span>(pipeline.vae.decode) | |
| <span class="hljs-comment"># CogVideoX works very well with long and well-described prompts</span> | |
| prompt = <span class="hljs-string">"A panda, dressed in a small, red jacket and a tiny hat, sits on a wooden stool in a serene bamboo forest. The panda's fluffy paws strum a miniature acoustic guitar, producing soft, melodic tunes. Nearby, a few other pandas gather, watching curiously and some clapping in rhythm. Sunlight filters through the tall bamboo, casting a gentle glow on the scene. The panda's face is expressive, showing concentration and joy as it plays. The background includes a small, flowing stream and vibrant green foliage, enhancing the peaceful and magical atmosphere of this unique musical performance."</span> | |
| video = pipeline(prompt=prompt, guidance_scale=<span class="hljs-number">6</span>, num_inference_steps=<span class="hljs-number">50</span>).frames[<span class="hljs-number">0</span>]`,wrap:!1}}),F=new ae({props:{code:"V2l0aG91dCUyMHRvcmNoLmNvbXBpbGUoKSUzQSUyMEF2ZXJhZ2UlMjBpbmZlcmVuY2UlMjB0aW1lJTNBJTIwVE9ETyUyMHNlY29uZHMuJTBBV2l0aCUyMHRvcmNoLmNvbXBpbGUoKSUzQSUyMEF2ZXJhZ2UlMjBpbmZlcmVuY2UlMjB0aW1lJTNBJTIwVE9ETyUyMHNlY29uZHMu",highlighted:`Without torch.compile(): Average inference <span class="hljs-built_in">time</span>: TODO <span class="hljs-built_in">seconds</span>. | |
| With torch.compile(): Average inference <span class="hljs-built_in">time</span>: TODO <span class="hljs-built_in">seconds</span>.`,wrap:!1}}),R=new Ge({props:{title:"CogVideoXPipeline",local:"diffusers.CogVideoXPipeline",headingTag:"h2"}}),S=new Ce({props:{name:"class diffusers.CogVideoXPipeline",anchor:"diffusers.CogVideoXPipeline",parameters:[{name:"tokenizer",val:": T5Tokenizer"},{name:"text_encoder",val:": T5EncoderModel"},{name:"vae",val:": AutoencoderKLCogVideoX"},{name:"transformer",val:": CogVideoXTransformer3DModel"},{name:"scheduler",val:": Union"}],parametersDescription:[{anchor:"diffusers.CogVideoXPipeline.vae",description:`<strong>vae</strong> (<a href="/docs/diffusers/pr_9017/en/api/models/autoencoderkl#diffusers.AutoencoderKL">AutoencoderKL</a>) — | |
| Variational Auto-Encoder (VAE) Model to encode and decode videos to and from latent representations.`,name:"vae"},{anchor:"diffusers.CogVideoXPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>T5EncoderModel</code>) — | |
| Frozen text-encoder. CogVideoX uses | |
| <a href="https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5EncoderModel" rel="nofollow">T5</a>; specifically the | |
| <a href="https://huggingface.co/PixArt-alpha/PixArt-alpha/tree/main/t5-v1_1-xxl" rel="nofollow">t5-v1_1-xxl</a> variant.`,name:"text_encoder"},{anchor:"diffusers.CogVideoXPipeline.tokenizer",description:`<strong>tokenizer</strong> (<code>T5Tokenizer</code>) — | |
| Tokenizer of class | |
| <a href="https://huggingface.co/docs/transformers/model_doc/t5#transformers.T5Tokenizer" rel="nofollow">T5Tokenizer</a>.`,name:"tokenizer"},{anchor:"diffusers.CogVideoXPipeline.transformer",description:`<strong>transformer</strong> (<a href="/docs/diffusers/pr_9017/en/api/models/cogvideox_transformer3d#diffusers.CogVideoXTransformer3DModel">CogVideoXTransformer3DModel</a>) — | |
| A text conditioned <code>CogVideoXTransformer3DModel</code> to denoise the encoded video latents.`,name:"transformer"},{anchor:"diffusers.CogVideoXPipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/pr_9017/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a>) — | |
| A scheduler to be used in combination with <code>transformer</code> to denoise the encoded video latents.`,name:"scheduler"}],source:"https://github.com/huggingface/diffusers/blob/vr_9017/src/diffusers/pipelines/cogvideo/pipeline_cogvideox.py#L133"}}),Q=new Ce({props:{name:"__call__",anchor:"diffusers.CogVideoXPipeline.__call__",parameters:[{name:"prompt",val:": Union = None"},{name:"negative_prompt",val:": Union = None"},{name:"height",val:": int = 480"},{name:"width",val:": int = 720"},{name:"num_frames",val:": int = 48"},{name:"fps",val:": int = 8"},{name:"num_inference_steps",val:": int = 50"},{name:"timesteps",val:": Optional = None"},{name:"guidance_scale",val:": float = 6"},{name:"use_dynamic_cfg",val:": bool = False"},{name:"num_videos_per_prompt",val:": int = 1"},{name:"eta",val:": float = 0.0"},{name:"generator",val:": Union = None"},{name:"latents",val:": Optional = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"output_type",val:": str = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"callback_on_step_end",val:": Union = None"},{name:"callback_on_step_end_tensor_inputs",val:": List = ['latents']"},{name:"max_sequence_length",val:": int = 226"}],parametersDescription:[{anchor:"diffusers.CogVideoXPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) — | |
| 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.CogVideoXPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) — | |
| The prompt or prompts not to guide the image generation. If not defined, one has to pass | |
| <code>negative_prompt_embeds</code> instead. Ignored when not using guidance (i.e., ignored if <code>guidance_scale</code> is | |
| less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.CogVideoXPipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to self.unet.config.sample_size * self.vae_scale_factor) — | |
| The height in pixels of the generated image. This is set to 1024 by default for the best results.`,name:"height"},{anchor:"diffusers.CogVideoXPipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to self.unet.config.sample_size * self.vae_scale_factor) — | |
| The width in pixels of the generated image. This is set to 1024 by default for the best results.`,name:"width"},{anchor:"diffusers.CogVideoXPipeline.__call__.num_frames",description:`<strong>num_frames</strong> (<code>int</code>, defaults to <code>48</code>) — | |
| Number of frames to generate. Must be divisible by self.vae_scale_factor_temporal. Generated video will | |
| contain 1 extra frame because CogVideoX is conditioned with (num_seconds * fps + 1) frames where | |
| num_seconds is 6 and fps is 4. However, since videos can be saved at any fps, the only condition that | |
| needs to be satisfied is that of divisibility mentioned above.`,name:"num_frames"},{anchor:"diffusers.CogVideoXPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 50) — | |
| 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.CogVideoXPipeline.__call__.timesteps",description:`<strong>timesteps</strong> (<code>List[int]</code>, <em>optional</em>) — | |
| Custom timesteps to use for the denoising process with schedulers which support a <code>timesteps</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. Must be in descending order.`,name:"timesteps"},{anchor:"diffusers.CogVideoXPipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 7.0) — | |
| Guidance scale as defined in <a href="https://arxiv.org/abs/2207.12598" rel="nofollow">Classifier-Free Diffusion Guidance</a>. | |
| <code>guidance_scale</code> is defined as <code>w</code> of equation 2. of <a href="https://arxiv.org/pdf/2205.11487.pdf" rel="nofollow">Imagen | |
| Paper</a>. Guidance scale is enabled by setting <code>guidance_scale > 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.`,name:"guidance_scale"},{anchor:"diffusers.CogVideoXPipeline.__call__.num_videos_per_prompt",description:`<strong>num_videos_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) — | |
| The number of videos to generate per prompt.`,name:"num_videos_per_prompt"},{anchor:"diffusers.CogVideoXPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code> or <code>List[torch.Generator]</code>, <em>optional</em>) — | |
| 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.CogVideoXPipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.FloatTensor</code>, <em>optional</em>) — | |
| 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 ge generated by sampling using the supplied random <code>generator</code>.`,name:"latents"},{anchor:"diffusers.CogVideoXPipeline.__call__.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.FloatTensor</code>, <em>optional</em>) — | |
| 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.CogVideoXPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.FloatTensor</code>, <em>optional</em>) — | |
| 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.CogVideoXPipeline.__call__.output_type",description:`<strong>output_type</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"pil"</code>) — | |
| 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.CogVideoXPipeline.__call__.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) — | |
| Whether or not to return a <code>~pipelines.stable_diffusion_xl.StableDiffusionXLPipelineOutput</code> instead | |
| of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.CogVideoXPipeline.__call__.callback_on_step_end",description:`<strong>callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) — | |
| 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.CogVideoXPipeline.__call__.callback_on_step_end_tensor_inputs",description:`<strong>callback_on_step_end_tensor_inputs</strong> (<code>List</code>, <em>optional</em>) — | |
| 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"},{anchor:"diffusers.CogVideoXPipeline.__call__.max_sequence_length",description:`<strong>max_sequence_length</strong> (<code>int</code>, defaults to <code>226</code>) — | |
| Maximum sequence length in encoded prompt. Must be consistent with | |
| <code>self.transformer.config.max_text_seq_length</code> otherwise may lead to poor results.`,name:"max_sequence_length"}],source:"https://github.com/huggingface/diffusers/blob/vr_9017/src/diffusers/pipelines/cogvideo/pipeline_cogvideox.py#L433",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script> | |
| <p><a | |
| href="/docs/diffusers/pr_9017/en/api/pipelines/cogvideox#diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput" | |
| >CogVideoXPipelineOutput</a> 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><a | |
| href="/docs/diffusers/pr_9017/en/api/pipelines/cogvideox#diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput" | |
| >CogVideoXPipelineOutput</a> or <code>tuple</code></p> | |
| `}}),Z=new lt({props:{anchor:"diffusers.CogVideoXPipeline.__call__.example",$$slots:{default:[pt]},$$scope:{ctx:A}}}),E=new Ce({props:{name:"encode_prompt",anchor:"diffusers.CogVideoXPipeline.encode_prompt",parameters:[{name:"prompt",val:": Union"},{name:"negative_prompt",val:": Union = None"},{name:"do_classifier_free_guidance",val:": bool = True"},{name:"num_videos_per_prompt",val:": int = 1"},{name:"prompt_embeds",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"max_sequence_length",val:": int = 226"},{name:"device",val:": Optional = None"},{name:"dtype",val:": Optional = None"}],parametersDescription:[{anchor:"diffusers.CogVideoXPipeline.encode_prompt.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) — | |
| prompt to be encoded`,name:"prompt"},{anchor:"diffusers.CogVideoXPipeline.encode_prompt.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) — | |
| The prompt or prompts not to guide the image generation. If not defined, one has to pass | |
| <code>negative_prompt_embeds</code> instead. Ignored when not using guidance (i.e., ignored if <code>guidance_scale</code> is | |
| less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.CogVideoXPipeline.encode_prompt.do_classifier_free_guidance",description:`<strong>do_classifier_free_guidance</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) — | |
| Whether to use classifier free guidance or not.`,name:"do_classifier_free_guidance"},{anchor:"diffusers.CogVideoXPipeline.encode_prompt.num_videos_per_prompt",description:`<strong>num_videos_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) — | |
| Number of videos that should be generated per prompt. torch device to place the resulting embeddings on`,name:"num_videos_per_prompt"},{anchor:"diffusers.CogVideoXPipeline.encode_prompt.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) — | |
| 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.CogVideoXPipeline.encode_prompt.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) — | |
| 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. | |
| device — (<code>torch.device</code>, <em>optional</em>): | |
| torch device | |
| dtype — (<code>torch.dtype</code>, <em>optional</em>): | |
| torch dtype`,name:"negative_prompt_embeds"}],source:"https://github.com/huggingface/diffusers/blob/vr_9017/src/diffusers/pipelines/cogvideo/pipeline_cogvideox.py#L229"}}),q=new Ge({props:{title:"CogVideoXPipelineOutput",local:"diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput",headingTag:"h2"}}),L=new Ce({props:{name:"class diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput",anchor:"diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput",parameters:[{name:"frames",val:": Tensor"}],parametersDescription:[{anchor:"diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput.frames",description:`<strong>frames</strong> (<code>torch.Tensor</code>, <code>np.ndarray</code>, or List[List[PIL.Image.Image]]) — | |
| List of video outputs - It can be a nested list of length <code>batch_size,</code> with each sub-list containing | |
| denoised PIL image sequences of length <code>num_frames.</code> It can also be a NumPy array or Torch tensor of shape | |
| <code>(batch_size, num_frames, channels, height, width)</code>.`,name:"frames"}],source:"https://github.com/huggingface/diffusers/blob/vr_9017/src/diffusers/pipelines/cogvideo/pipeline_cogvideox.py#L118"}}),D=new rt({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/cogvideox.md"}}),{c(){a=l("meta"),v=s(),p=l("p"),w=s(),m(T.$$.fragment),d=s(),J=l("p"),J.innerHTML=Ne,le=s(),G=l("p"),G.textContent=Pe,re=s(),V=l("p"),V.innerHTML=ze,de=s(),m(x.$$.fragment),pe=s(),B=l("p"),B.innerHTML=Fe,ce=s(),m(X.$$.fragment),me=s(),W=l("p"),W.innerHTML=Re,ue=s(),$=l("p"),$.textContent=Se,fe=s(),m(k.$$.fragment),ge=s(),H=l("p"),H.innerHTML=Qe,he=s(),m(Y.$$.fragment),_e=s(),N=l("p"),N.textContent=Ee,Me=s(),m(P.$$.fragment),be=s(),z=l("p"),z.textContent=qe,we=s(),m(F.$$.fragment),ye=s(),m(R.$$.fragment),Te=s(),b=l("div"),m(S.$$.fragment),Ve=s(),O=l("p"),O.textContent=Le,Be=s(),K=l("p"),K.innerHTML=De,Xe=s(),U=l("div"),m(Q.$$.fragment),We=s(),ee=l("p"),ee.textContent=Ae,$e=s(),m(Z.$$.fragment),ke=s(),C=l("div"),m(E.$$.fragment),He=s(),te=l("p"),te.textContent=Oe,Je=s(),m(q.$$.fragment),ve=s(),j=l("div"),m(L.$$.fragment),Ye=s(),ne=l("p"),ne.textContent=Ke,Ue=s(),m(D.$$.fragment),je=s(),ie=l("p"),this.h()},l(e){const t=it("svelte-u9bgzb",document.head);a=r(t,"META",{name:!0,content:!0}),t.forEach(n),v=i(e),p=r(e,"P",{}),oe(p).forEach(n),w=i(e),u(T.$$.fragment,e),d=i(e),J=r(e,"P",{"data-svelte-h":!0}),M(J)!=="svelte-1wuowka"&&(J.innerHTML=Ne),le=i(e),G=r(e,"P",{"data-svelte-h":!0}),M(G)!=="svelte-1cwsb16"&&(G.textContent=Pe),re=i(e),V=r(e,"P",{"data-svelte-h":!0}),M(V)!=="svelte-19oae4l"&&(V.innerHTML=ze),de=i(e),u(x.$$.fragment,e),pe=i(e),B=r(e,"P",{"data-svelte-h":!0}),M(B)!=="svelte-14a2tju"&&(B.innerHTML=Fe),ce=i(e),u(X.$$.fragment,e),me=i(e),W=r(e,"P",{"data-svelte-h":!0}),M(W)!=="svelte-iekg51"&&(W.innerHTML=Re),ue=i(e),$=r(e,"P",{"data-svelte-h":!0}),M($)!=="svelte-jub7f1"&&($.textContent=Se),fe=i(e),u(k.$$.fragment,e),ge=i(e),H=r(e,"P",{"data-svelte-h":!0}),M(H)!=="svelte-4294wb"&&(H.innerHTML=Qe),he=i(e),u(Y.$$.fragment,e),_e=i(e),N=r(e,"P",{"data-svelte-h":!0}),M(N)!=="svelte-9i4prs"&&(N.textContent=Ee),Me=i(e),u(P.$$.fragment,e),be=i(e),z=r(e,"P",{"data-svelte-h":!0}),M(z)!=="svelte-3zu8e7"&&(z.textContent=qe),we=i(e),u(F.$$.fragment,e),ye=i(e),u(R.$$.fragment,e),Te=i(e),b=r(e,"DIV",{class:!0});var y=oe(b);u(S.$$.fragment,y),Ve=i(y),O=r(y,"P",{"data-svelte-h":!0}),M(O)!=="svelte-gmblkq"&&(O.textContent=Le),Be=i(y),K=r(y,"P",{"data-svelte-h":!0}),M(K)!=="svelte-19f99bm"&&(K.innerHTML=De),Xe=i(y),U=r(y,"DIV",{class:!0});var I=oe(U);u(Q.$$.fragment,I),We=i(I),ee=r(I,"P",{"data-svelte-h":!0}),M(ee)!=="svelte-v78lg8"&&(ee.textContent=Ae),$e=i(I),u(Z.$$.fragment,I),I.forEach(n),ke=i(y),C=r(y,"DIV",{class:!0});var xe=oe(C);u(E.$$.fragment,xe),He=i(xe),te=r(xe,"P",{"data-svelte-h":!0}),M(te)!=="svelte-16q0ax1"&&(te.textContent=Oe),xe.forEach(n),y.forEach(n),Je=i(e),u(q.$$.fragment,e),ve=i(e),j=r(e,"DIV",{class:!0});var Ze=oe(j);u(L.$$.fragment,Ze),Ye=i(Ze),ne=r(Ze,"P",{"data-svelte-h":!0}),M(ne)!=="svelte-1qnvsrt"&&(ne.textContent=Ke),Ze.forEach(n),Ue=i(e),u(D.$$.fragment,e),je=i(e),ie=r(e,"P",{}),oe(ie).forEach(n),this.h()},h(){se(a,"name","hf:doc:metadata"),se(a,"content",mt),se(U,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),se(C,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),se(b,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),se(j,"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){c(document.head,a),o(e,v,t),o(e,p,t),o(e,w,t),f(T,e,t),o(e,d,t),o(e,J,t),o(e,le,t),o(e,G,t),o(e,re,t),o(e,V,t),o(e,de,t),f(x,e,t),o(e,pe,t),o(e,B,t),o(e,ce,t),f(X,e,t),o(e,me,t),o(e,W,t),o(e,ue,t),o(e,$,t),o(e,fe,t),f(k,e,t),o(e,ge,t),o(e,H,t),o(e,he,t),f(Y,e,t),o(e,_e,t),o(e,N,t),o(e,Me,t),f(P,e,t),o(e,be,t),o(e,z,t),o(e,we,t),f(F,e,t),o(e,ye,t),f(R,e,t),o(e,Te,t),o(e,b,t),f(S,b,null),c(b,Ve),c(b,O),c(b,Be),c(b,K),c(b,Xe),c(b,U),f(Q,U,null),c(U,We),c(U,ee),c(U,$e),f(Z,U,null),c(b,ke),c(b,C),f(E,C,null),c(C,He),c(C,te),o(e,Je,t),f(q,e,t),o(e,ve,t),o(e,j,t),f(L,j,null),c(j,Ye),c(j,ne),o(e,Ue,t),f(D,e,t),o(e,je,t),o(e,ie,t),Ie=!0},p(e,[t]){const y={};t&2&&(y.$$scope={dirty:t,ctx:e}),x.$set(y);const I={};t&2&&(I.$$scope={dirty:t,ctx:e}),Z.$set(I)},i(e){Ie||(g(T.$$.fragment,e),g(x.$$.fragment,e),g(X.$$.fragment,e),g(k.$$.fragment,e),g(Y.$$.fragment,e),g(P.$$.fragment,e),g(F.$$.fragment,e),g(R.$$.fragment,e),g(S.$$.fragment,e),g(Q.$$.fragment,e),g(Z.$$.fragment,e),g(E.$$.fragment,e),g(q.$$.fragment,e),g(L.$$.fragment,e),g(D.$$.fragment,e),Ie=!0)},o(e){h(T.$$.fragment,e),h(x.$$.fragment,e),h(X.$$.fragment,e),h(k.$$.fragment,e),h(Y.$$.fragment,e),h(P.$$.fragment,e),h(F.$$.fragment,e),h(R.$$.fragment,e),h(S.$$.fragment,e),h(Q.$$.fragment,e),h(Z.$$.fragment,e),h(E.$$.fragment,e),h(q.$$.fragment,e),h(L.$$.fragment,e),h(D.$$.fragment,e),Ie=!1},d(e){e&&(n(v),n(p),n(w),n(d),n(J),n(le),n(G),n(re),n(V),n(de),n(pe),n(B),n(ce),n(me),n(W),n(ue),n($),n(fe),n(ge),n(H),n(he),n(_e),n(N),n(Me),n(be),n(z),n(we),n(ye),n(Te),n(b),n(Je),n(ve),n(j),n(Ue),n(je),n(ie)),n(a),_(T,e),_(x,e),_(X,e),_(k,e),_(Y,e),_(P,e),_(F,e),_(R,e),_(S),_(Q),_(Z),_(E),_(q,e),_(L),_(D,e)}}}const mt='{"title":"CogVideoX","local":"cogvideox","sections":[{"title":"Inference","local":"inference","sections":[],"depth":2},{"title":"CogVideoXPipeline","local":"diffusers.CogVideoXPipeline","sections":[],"depth":2},{"title":"CogVideoXPipelineOutput","local":"diffusers.pipelines.cogvideo.pipeline_cogvideox.CogVideoXPipelineOutput","sections":[],"depth":2}],"depth":1}';function ut(A){return nt(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class yt extends ot{constructor(a){super(),st(this,a,ut,ct,tt,{})}}export{yt as component}; | |
Xet Storage Details
- Size:
- 37.1 kB
- Xet hash:
- 4acd7f9434d53d50f897b7b5efd49f32171c4c3d293764f9ae57ae3bc212a6ca
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.