Pero ninguno de los vídeos publicados en el blog post de Sora o en el technical report están editados. Los vídeos que dices son los creados por los artistas usando Sora en el proceso, y ahí es normal que cada uno post-procese los outputs. Diría que no es la misma comparación.
CREATIVE AI
-
SDXL Inpainting: AI-Powered Photo Restoration and Enhancement
By
–
🚀 New Blog Alert 🚀https://t.co/APFmuTsB6F
— Satya Mallick (@LearnOpenCV) 1 mai 2024
Our latest blog post unveils the power of SDXL inpainting—where cutting-edge AI meets photo restoration. Discover how to enhance and reimagine your cherished memories effortlessly!#sdxl #inpainting #computervision #deeplearning #ai pic.twitter.com/Phiad92GzLNew Blog Alert https://
learnopencv.com/sdxl-inpaintin
g/
… Our latest blog post unveils the power of SDXL inpainting—where cutting-edge AI meets photo restoration. Discover how to enhance and reimagine your cherished memories effortlessly! #sdxl #inpainting #computervision #deeplearning #ai -
Key to Successful Image Generation: Avoid Typical AI Look
By
–
The key to using image generation AI successfully is to produce images that don’t look like the typical AI-generated images.
-
Use ChatGPT prompts to create stunning presentations in minutes
By
–
Use these ChatGPT prompts to create stunning presentations in minutes: [bookmark Bookmark for later]
-
LLMs are poor judges of ASCII art, votes should be excluded
By
–
Human preference LLM arenas are poorly suited for evaluating ASCII art because the ASCII art that most impresses a human is often verbatim regurgitation of an existing human work and this is rarely true for text. Votes on ASCII art should be detected and thrown out IMO.
-
TikTok Develops Voice Cloning Feature with User Control
By
–
TikTok is working on a new feature that lets users clone their voice. Users will have full control over their AI voice. http://
theaivalley.com/p/voicecloning via @heyBarsee #AI #IoT #5G #GenerativeAI #Video #Clips @SpirosMargaris @pierrepinna @DeepLearn007 @Analytics_699 @gvalan @Hal_Good -
China Releases Vidu: OpenAI Sora Competitor for Realistic Video Generation
By
–
China just released OpenAI’s Sora rival “Vidu” which can create realistic clips in seconds.
— Harold Sinnott #MWC26 (@HaroldSinnott) 28 avril 2024
via @heyBarsee #AI #IoT #5G #GenerativeAI #Video #Clips @SpirosMargaris @pierrepinna @DeepLearn007 @Analytics_699 @gvalan @Hal_Good pic.twitter.com/rQLqnnGPbXChina just released OpenAI’s Sora rival “Vidu” which can create realistic clips in seconds. via @heyBarsee #AI #IoT #5G #GenerativeAI #Video #Clips @SpirosMargaris @pierrepinna @DeepLearn007 @Analytics_699 @gvalan @Hal_Good
-
Ken Goldberg participates in Art and AI panel discussion
By
–
Looking fwd to panel at 5pm today on Art and AI at show curated by @profjsb
-
Midjourney’s New Random Style Reference Feature for Cute Dogs
By
–
Midjourney's new random style reference feature is super fun. A while bunch of examples of "cute doggie –sref random"
-
China unveils Vidu, AI video generator rivaling OpenAI’s Sora
By
–
Overnight, China released their own version of OpenAI’s Sora:
— AI Breakfast (@AiBreakfast) 27 avril 2024
AI video generator “Vidu” can create 16 second clips at 1080p:pic.twitter.com/LkACnl1M2oOvernight, China released their own version of OpenAI’s Sora: AI video generator “Vidu” can create 16 second clips at 1080p: