{"id":6558,"date":"2025-10-09T18:33:29","date_gmt":"2025-10-09T10:33:29","guid":{"rendered":"https:\/\/infernews.com\/?p=6558"},"modified":"2025-10-09T18:47:46","modified_gmt":"2025-10-09T10:47:46","slug":"ovi-%e7%94%9f%e6%88%90%e8%a6%96%e9%a0%bb%e3%80%81%e5%b0%8d%e5%98%b4%e9%9f%b3%e9%a0%bb","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/ovi-%e7%94%9f%e6%88%90%e8%a6%96%e9%a0%bb%e3%80%81%e5%b0%8d%e5%98%b4%e9%9f%b3%e9%a0%bb\/","title":{"rendered":"Ovi \u751f\u6210\u8996\u983b\u3001\u5c0d\u5634\u97f3\u983b"},"content":{"rendered":"\n<p><a href=\"https:\/\/aaxwaz.github.io\/Ovi\/\">Ovi<\/a> \u4f7f\u7528\u4e86\u5c08\u5c6c\u9810\u8a13\u7df4 5B \u97f3\u983b\u5206\u652f\uff0c\u67b6\u69cb\u8a2d\u8a08\u985e\u4f3c WAN 2.2 5B\uff0c\u540c\u6642\u63d0\u4f9b\u4e86 1B \u878d\u5408\u5206\u652f\uff0c\u652f\u6301\u7d14\u6587\u672c\u6216\u6587\u672c+\u5716\u7247\u8f38\u5165\uff0c\u81ea\u52d5\u751f\u6210\u8996\u983b\u3001\u5c0d\u5634\u97f3\u983b\uff0c\u4ee5\u53ca\u5339\u914d\u5834\u666f\u7684\u80cc\u666f\u97f3\u6548\u548c\u97f3\u6a02\u3002<\/p>\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"Finally, open-source AI video with SOUND! Ovi tutorial\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_w9WmKGxTTdI\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fw9WmKGxTTdI%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/w9WmKGxTTdI\" \/><meta itemprop=\"duration\" content=\"PT18M4S\" \/><meta itemprop=\"uploadDate\" content=\"2025-10-09T02:08:57Z\" \/><\/div><div id=\"lyte_w9WmKGxTTdI\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fw9WmKGxTTdI%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">Finally, open-source AI video with SOUND! Ovi tutorial<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/w9WmKGxTTdI\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2Fw9WmKGxTTdI%2F0.jpg\" alt=\"Finally, open-source AI video with SOUND! Ovi tutorial\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"Ovi full installation tutorial. How to use Ovi in ComfyUI #ai #aitools #aivideo #veo3 #sora2 Thanks to our sponsor LTX Studio. Try it for free https:\/\/tinyurl.com\/25wrkwap Ovi project page: https:\/\/aaxwaz.github.io\/Ovi\/ ComfyUI workflow: https:\/\/github.com\/snicolast\/ComfyUI-Ovi ComfyUI tutorial: https:\/\/youtu.be\/g74Cq9Ip2ik Wavespeed https:\/\/wavespeed.ai\/models\/character-ai\/ovi\/text-to-video Fal https:\/\/fal.ai\/models\/fal-ai\/ovi\/image-to-video Replicate https:\/\/replicate.com\/character-ai\/ovi-i2v 0:00 Ovi intro 0:30 Ovi demos 3:47 How to use Ovi online 4:47 How to install Ovi offline 7:57 LTX Studio 9:13 Ovi installation continued 11:17 How to use Ovi in ComfyUI 15:16 T2V 15:53 I2V Newsletter: https:\/\/aisearch.substack.com\/ Find AI tools &amp; jobs: https:\/\/ai-search.io\/ Support: https:\/\/ko-fi.com\/aisearch Here&#039;s my equipment, in case you&#039;re wondering: Lenovo Thinkbook: https:\/\/amzn.to\/4jWeKwH Dell Precision 5690: https:\/\/www.dell.com\/en-us\/dt\/ai-technologies\/index.htm?utm_source=AISearchTools&amp;utm_medium=youtube&amp;utm_campaign=precisionai#tab0=0 GPU: Nvidia RTX 5000 Ada https:\/\/nvda.ws\/3zfqGqS Mic: Shure SM7B https:\/\/amzn.to\/3DErjt1 Audio interface: Scarlett Solo https:\/\/amzn.to\/3qELMeu\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"OVI ComfyUI Workflow: Image &amp;amp; Text-to-Video with Sound (2025) &mdash; Is It Better Than Veo 3?\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_64AK76-qZKI\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F64AK76-qZKI%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/64AK76-qZKI\" \/><meta itemprop=\"duration\" content=\"PT11M22S\" \/><meta itemprop=\"uploadDate\" content=\"2025-10-08T22:39:30Z\" \/><\/div><div id=\"lyte_64AK76-qZKI\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F64AK76-qZKI%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">OVI ComfyUI Workflow: Image &amp; Text-to-Video with Sound (2025) \u2014 Is It Better Than Veo 3?<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/64AK76-qZKI\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2F64AK76-qZKI%2F0.jpg\" alt=\"OVI ComfyUI Workflow: Image &amp;amp; Text-to-Video with Sound (2025) &mdash; Is It Better Than Veo 3?\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"I am using OVI in ComfyUI to make short videos with voice and sound from a single prompt. In this guide I show you how I set up the OVI ComfyUI workflow, fix missing nodes, and render clips with clear audio. You have to update ComfyUI before you start so everything loads the right way. We start clean. I upload the workflow, open it in ComfyUI, and fix red nodes with Manager Install Missing Custom Nodes. When the graph opens, you will see a node called OVI Engine Loader. That means it is ready. Next I explain the OVI node. It is the main part that makes video from text or from an image. There are two model builds, FP8 and BF16. If your GPU has low VRAM, set CPU Offload to True. That keeps it stable on 12 GB and 16 GB cards. I show the files you need and the folders to use. You download the text encoder, the VAE, and the OVI model build you want. In my tests, the FP8 build is smaller and works well on mid GPUs. The BF16 build is larger and gives a bit more detail on 24 GB cards or higher. Then we tune settings. You will see OVI Attention Selector. If you do not have Seg Attention, keep it on Auto. If you have Seg Attention, turn it on for faster renders. For quality, I get the best balance with 50 steps. If your GPU is limited, use 30 to 36 steps and it still looks good. For resolution, I stay close to 720 x 720. It keeps the quality high and the performance smooth. You can also use 960 x 540 for landscape or 540 x 960 for vertical. Now the prompt. This is the fun part. OVI understands a full scene from one line. You can add a voice line and background sound inside the same prompt. It uses two simple tags. The S tag is for speech. The AudioCap tag is for background sound. For one test I wrote a stage scene, then added a short line in the S tag and a guitar crowd mix in the AudioCap tag. The clip came out with lip sync and sound in time with the motion. I also test text to video and image to video. Faces stay clear, lighting feels natural, and the lines are spoken in sync. I try scenes with emotion and two speakers. You will see a tense room, a quiet portrait, and a festive background. Each one renders with solid motion and clean audio. If you want to try it, the model links are below. Watch till the end to learn the full OVI ComfyUI workflow, from setup to your first talking clip. In the next video I will show my low VRAM tests and share what settings worked best. Workflow: https:\/\/aistudynow.com\/ovi-comfyui-workflow-guide-2025-text-image-to-video-with-sound\/ Files You Need To Download: #OVI #ComfyUI #TextToVideo #AIVideo\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>","protected":false},"excerpt":{"rendered":"<p>Ovi \u4f7f\u7528\u4e86\u5c08\u5c6c\u9810\u8a13\u7df4 5B \u97f3\u983b\u5206\u652f\uff0c\u67b6\u69cb\u8a2d\u8a08\u985e\u4f3c WAN 2.2 5B\uff0c\u540c\u6642\u63d0\u4f9b\u4e86 1B \u878d\u5408\u5206\u652f\uff0c\u652f\u6301\u7d14\u6587\u672c\u6216\u6587\u672c+\u5716\u7247\u8f38\u5165\uff0c\u81ea\u52d5\u751f\u6210\u8996\u983b\u3001\u5c0d\u5634\u97f3\u983b\uff0c\u4ee5\u53ca\u5339\u914d\u5834\u666f\u7684\u80cc\u666f\u97f3\u6548\u548c\u97f3\u6a02\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"googlesitekit_rrm_CAowvqSiDA:productID":"","footnotes":""},"categories":[125,126,133],"tags":[],"class_list":["post-6558","post","type-post","status-publish","format-standard","hentry","category-comfyui","category-126","category-133"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/6558","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=6558"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/6558\/revisions"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=6558"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=6558"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=6558"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}