Загрузка видео...

Не удалось загрузить видео

На главную

moshi moshi, happy monday! 😻 so here it comes: Moshi Desktop - a 7 mb web app built into moshi-hook - works locally or with any remote host running herdr/moshi - agents, workspaces, terminals, chat, file browsing, diff viewing, and more this is the very first version, so there...

53,520 просмотров • 12 дней назад •via X (Twitter)

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

7️⃣: As Rin said, the reason I cried was because they were tears of happiness. As everyone can see, both of us have been in this industry for a very long time-10 years already. I was the one who sitting down there watching. I never had the chance to stand on stage or perform. This is probably the very first time that I get to perform a solo stage and truly do something I really want to do. I wanted to express my true feelings to everyone, and I never thought that I would have a day like this-a day where so many people would come to see me like this. Honestly, in the past, if just 10 people came to see me, I was already happy. Even if there were only one person left, I would still be very, very happy. So I never thought there would be a day where the hall is completely filled with people coming to see us, and where we receive love from so many different countries. I want to thank everyone so, so much for loving the work that both of us create. And we’ve become a safe zone for all of you.🥰 Let me stop here for now. If there’s anything more, I’ll continue later. I’ll let P’Kao speak. 9️⃣: Is Nong amazing? Phi will always be by your side, always standing behind you, and will stay by your side forever. You know, Nong have been through a lot of pressure, and also gone through so many expectations. I truly understand that being here is not easy. Getting into this career might be easy, but continuing to move forward like this is very, very difficult. And you’ve had to face so many things…I just want you to stay strong. 7️⃣: I also want to say that P’Kao is the same. P’Kao is someone who is very, very talented, and I want her to be confident in herself because she can do anything. P’Kao is truly amazing, and I want her to be this happy, to be a source of happiness for everyone. As everyone has seen, P’Kao always encourages people, always asks things like “Have you eaten yet?” That really is who she is someone who always takes care of others. Sometimes, she may forget to think about herself. So I want you to think about yourself more, to love yourself more, because everyone here loves you so, so much and I do too. I’ll always be right here. Whenever you turn around, you’ll see KaiYeh right here. LOVE DESIGN 1ST DRAWING #LoveDesign1stFanMeetTH

KaoJaneMood

42,233 просмотров • 9 месяцев назад

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,841 просмотров • 11 месяцев назад