#text2video — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #text2video, aggregated by home.social.
-
@aisearch.bsky.social 🤖 🤪
This new #AI edits any video! FREE & offline
https://youtu.be/XSECbTkgRl8?si=nOQwScq3tSJ5OFew
#genai #wan25 #text2video editor
10/24/2025
-
@aisearch.bsky.social 🤖 🤪
This new #AI edits any video! FREE & offline
https://youtu.be/XSECbTkgRl8?si=nOQwScq3tSJ5OFew
#genai #wan25 #text2video editor
10/24/2025
-
Huh, Sora 2 knows a lot of things:
“Ethan Mollick parachuting into a volcano, explains the three forms of legitimation from DiMaggio, Paul; Powell, Walter. (April 1983). "The iron cage revisited: institutional isomorphism and collective rationality in organizational fields"
(Only 15 second limit)
🧵 https://bsky.app/profile/emollick.bsky.social/post/3m2cujras5s27
-
Huh, Sora 2 knows a lot of things:
“Ethan Mollick parachuting into a volcano, explains the three forms of legitimation from DiMaggio, Paul; Powell, Walter. (April 1983). "The iron cage revisited: institutional isomorphism and collective rationality in organizational fields"
(Only 15 second limit)
🧵 https://bsky.app/profile/emollick.bsky.social/post/3m2cujras5s27
-
Last evening, I spent some time investigating how to generate video from a text prompt and created this short clip. I was thinking it would require more GPU power, but all worked out OK. Took around 100 seconds to create this clip. The model used is Wan2.1, a 1.3b parameter model that fits a 8GB VRAM GPU (AMD/Nvidia). I used ComfyUI running on my home lab. Impressive for a "tiny" model, but comes to demonstrate that model size does not equate to results. Give the little models a go. You may surprise yourself with the results.
-
Last evening, I spent some time investigating how to generate video from a text prompt and created this short clip. I was thinking it would require more GPU power, but all worked out OK. Took around 100 seconds to create this clip. The model used is Wan2.1, a 1.3b parameter model that fits a 8GB VRAM GPU (AMD/Nvidia). I used ComfyUI running on my home lab. Impressive for a "tiny" model, but comes to demonstrate that model size does not equate to results. Give the little models a go. You may surprise yourself with the results.
-
-
-
@theaigrid
Runways Text To Video "GEN 4" Actually Changes The Industry!
-
@theaigrid
Runways Text To Video "GEN 4" Actually Changes The Industry!
-
@aisearch.bsky.social
Full length AI videos, realtime AI voice, free AI #VFX, 3D scene generator, new AI image tools 🧰
#ai #lllm #text2video
https://youtu.be/yUylxQcXu6c?feature=shared -
@aisearch.bsky.social
Full length AI videos, realtime AI voice, free AI #VFX, 3D scene generator, new AI image tools 🧰
#ai #lllm #text2video
https://youtu.be/yUylxQcXu6c?feature=shared -
@wesroth #Ai #Agi #Text2Video #Sora #OpenAi
Ep 12-9-2024
"FULL RELEASE of SORA! OpenAI Begins New Age of AI Video | UNLIMITED $200 version tested."
-
@wesroth #Ai #Agi #Text2Video #Sora #OpenAi
Ep 12-9-2024
"FULL RELEASE of SORA! OpenAI Begins New Age of AI Video | UNLIMITED $200 version tested."
-
Sora von OpenAI, ist ein innovatives Text-zu-Video-Modell, es ermöglicht die Erzeugung lebensechter Video Szenen durch Sprachverarbeitung und Diffusionsmodelltechnologie. Videos bis zu einer Minute Länge sind möglich. Simulation von Physik und räumlicher Orientierung sind eine Herausforderung. #openai #sora #text2video
-
Good first review of Sora by Marques Brownlee , balanced with attention to the potential but also the large risks. "This is the worst that this technology is going to be..."
https://youtu.be/NXpdyAWLDas?si=8zZ5Ap6_PhhCNNtR
#Sora #AI #GenerativeAI #text2video #openai #MarquesBrownlee -
Good first review of Sora by Marques Brownlee , balanced with attention to the potential but also the large risks. "This is the worst that this technology is going to be..."
https://youtu.be/NXpdyAWLDas?si=8zZ5Ap6_PhhCNNtR
#Sora #AI #GenerativeAI #text2video #openai #MarquesBrownlee -
Google’s latest AI video generator renders implausible situations for cute animals - Enlarge / Still images of AI-generated video examples provided by Googl... - https://arstechnica.com/?p=1998725 #machinelearning #imagesynthesis #videosynthesis #text-to-video #text2video #lumiere #biz #google #ai
-
Google’s latest AI video generator renders implausible situations for cute animals - Enlarge / Still images of AI-generated video examples provided by Googl... - https://arstechnica.com/?p=1998725 #machinelearning #imagesynthesis #videosynthesis #text-to-video #text2video #lumiere #biz #google #ai
-
Show HN: Comflowy – A ComfyUI Tutorial for Beginners
https://www.comflowy.com/
#ycombinator #ComfyUI #Stable_Diffusion #comflowy #stable_diffusion #stable_diffusion_webui #sd_next #comfy #ui_library #text_to_image #text2img #text2video #text_to_video #ComfyUI_教程 #ComfyUI_tutorial #How_to_use_ComfyUI #ComfyUI_使用教程 #如何使用ComfyUI -
Show HN: Comflowy – A ComfyUI Tutorial for Beginners
https://www.comflowy.com/
#ycombinator #ComfyUI #Stable_Diffusion #comflowy #stable_diffusion #stable_diffusion_webui #sd_next #comfy #ui_library #text_to_image #text2img #text2video #text_to_video #ComfyUI_教程 #ComfyUI_tutorial #How_to_use_ComfyUI #ComfyUI_使用教程 #如何使用ComfyUI -
Foi lançada IA que faz vídeo a partir de texto: https://www.youtube.com/watch?v=BpoOVEEDiFA
Já quero fazer um curta-metragem.
-
check out this brilliant summary of the latest generative ai art news by @aiflux
#AI #generativeAI #aiart #ar #vr #virtualreality #stablediffusion #nvidia #texttovideo #Text2video
-
"Will Smith eating spaghetti" created with the open source "text2video" ModelScope AI.
We can do this now! In seconds and without having to fool around with deepfake tools for hours. Now imagine what would be possible in just 12 months from now!
Yes, we do have to slow down when it comes to generative AI. Otherwise this won't end well!
-
"Will Smith eating spaghetti" created with the open source "text2video" ModelScope AI.
We can do this now! In seconds and without having to fool around with deepfake tools for hours. Now imagine what would be possible in just 12 months from now!
Yes, we do have to slow down when it comes to generative AI. Otherwise this won't end well!
-
Generated by the new Modelscope text-to-video, an algorithmically-generated Will Smith shovels down a bizarro pasta meal.
https://www.vice.com/en/article/xgw8ek/ai-will-smith-eating-spaghetti-hill-haunt-you-for-the-rest-of-your-life
#AI #modelscope #text2video -
Generated by the new Modelscope text-to-video, an algorithmically-generated Will Smith shovels down a bizarro pasta meal.
https://www.vice.com/en/article/xgw8ek/ai-will-smith-eating-spaghetti-hill-haunt-you-for-the-rest-of-your-life
#AI #modelscope #text2video -
Written and Directed by ChatGPT.
Watch and read about the process
=> https://bits-next.p1x.in/written-and-directed-by-chatgpt.html -
Written and Directed by ChatGPT.
Watch and read about the process
=> https://bits-next.p1x.in/written-and-directed-by-chatgpt.html -
-
-
Meta announces Make-A-Video, which generates video from text - Enlarge / Still image from an AI-generated video of a teddy bear painti... - https://arstechnica.com/?p=1885529 #machinelearning #imagesynthesis #make-a-video #text2video #biz&it #metaai #meta #ai
-
Runway teases AI-powered text-to-video editing using written prompts - Enlarge / A still from Runway's "Text to Video" teaser promo suggesting... - https://arstechnica.com/?p=1879936 #machinelearning #stablediffusion #videosynthesis #videoediting #text2video #cogvideo #biz&it #runway #video
