EyeingAI (@EyeingAI)
전체 오디오-비디오 모델이 오픈소스로 공개되었다는 폭발적인 발표. 4K 비디오, 50fps, 오디오와 사운드 디자인 동기화, LoRA 지원, 훈련 코드 및 전체 워크플로우 포함하며 GPU에서 자체 실행 가능하다고 강조합니다. 공개물이 Adobe, Runway, Pika 등 상용 툴들에 맞먹는 매우 포괄적 OSS 릴리스라고 소개합니다.
WTF... They open-sourced an ENTIRE audio-video model. – 4K video – 50fps – Synced audio + sound design – LoRAs, training code, full workflows – Runs entirely on your GPU Adobe, Runway, Pika… close your tabs. 😭 Here’s why this is the most complete OSS drop ever: 🧵
157 - Eric Kinkaid of Loras [R] v. Zane Licht of Wartburg [G]
285 - Sam Costello of Loras [R] v. David Ortiz of Elmhurst College [G]
184 - Jack Callen of UW-Stevens Point [R] v. Landry Barker of Loras [G]
184 - Devin Rogers of Carthage College [R] v. Aiden Rice of Loras [G]
FLOORJAM 007 with Ell Murphy, blissy e, LORA S, Baba T & Drey @ Next Door Records Two - 30 Aug feat. Ell Murphy, LORA S, blissy e + more
This week's post on the Diffusion Doodles Substack (https://diffusiondoodles.substack.com/p/how-to-train-a-lora) looks at creating your own LoRAs for consistent styles and characters.
#GenAI #diffusionmodels #imagegeneration #comfyUI #flux #loras #characterdesign
🚀 New Video Alert!
Explore advanced image generation with Stable Diffusion in our latest "GenAI's Lamp" tutorial. Learn how to use #Embeddings and #LoRAs to create stunning visuals.
Watch now! 🎨
✨ https://youtu.be/mZ6eVw8-MM8
sayzard
videovortex
SESH.sx
Chris Green
Raphiki
Peter Morse Studio