We find a new set of use cases for Stable Audio Open ( @jordiponsdotme.bsky.social, @stabilityai.bsky.social, @hf.co) and other large pretrained audio generative models, like AudioLDM and beyond!
May 9, 2025 at 4:06 PM
We find a new set of use cases for Stable Audio Open ( @jordiponsdotme.bsky.social, @stabilityai.bsky.social, @hf.co) and other large pretrained audio generative models, like AudioLDM and beyond!
"Curses"
Various explorations in fusing audio automation techniques and sound design along with granular synthesis.
Mp3 Version Available for Free 📂✨[t.ly/smQ78]
#AudioLDM #StableAudio #MaxMsp #Generative #Ambient #Drone #Vaporwave #Experimental #Glitch
Various explorations in fusing audio automation techniques and sound design along with granular synthesis.
Mp3 Version Available for Free 📂✨[t.ly/smQ78]
#AudioLDM #StableAudio #MaxMsp #Generative #Ambient #Drone #Vaporwave #Experimental #Glitch
October 2, 2024 at 1:47 PM
"Curses"
Various explorations in fusing audio automation techniques and sound design along with granular synthesis.
Mp3 Version Available for Free 📂✨[t.ly/smQ78]
#AudioLDM #StableAudio #MaxMsp #Generative #Ambient #Drone #Vaporwave #Experimental #Glitch
Various explorations in fusing audio automation techniques and sound design along with granular synthesis.
Mp3 Version Available for Free 📂✨[t.ly/smQ78]
#AudioLDM #StableAudio #MaxMsp #Generative #Ambient #Drone #Vaporwave #Experimental #Glitch
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models https://huggingface.co/spaces/haoheliu/audioldm-text-to-audio-generation
August 14, 2023 at 5:20 PM
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models https://huggingface.co/spaces/haoheliu/audioldm-text-to-audio-generation
How I Built a Full AI Studio for 6GB VRAM Cards (In 9 Hours of AI-Assisted Chaos)
A GTX 1660 Ti with 6GB VRAM struggles with modern diffusion models, throwing OOM errors and black image bugs. Instead of upgrading hardware, this build forces FP32 precision, adds attention …
#hackernews #news #nvidia
A GTX 1660 Ti with 6GB VRAM struggles with modern diffusion models, throwing OOM errors and black image bugs. Instead of upgrading hardware, this build forces FP32 precision, adds attention …
#hackernews #news #nvidia
How I Built a Full AI Studio for 6GB VRAM Cards (In 9 Hours of AI-Assisted Chaos)
A GTX 1660 Ti with 6GB VRAM struggles with modern diffusion models, throwing OOM errors and black image bugs. Instead of upgrading hardware, this build forces FP32 precision, adds attention and VAE slicing, and wraps Stable Diffusion, AnimateDiff, and AudioLDM into a unified Streamlit-based local studio. The result is a stable, open-source generative AI hub optimized for mid-range Nvidia GPUs.
hackernoon.com
March 3, 2026 at 6:48 PM
How I Built a Full AI Studio for 6GB VRAM Cards (In 9 Hours of AI-Assisted Chaos)
A GTX 1660 Ti with 6GB VRAM struggles with modern diffusion models, throwing OOM errors and black image bugs. Instead of upgrading hardware, this build forces FP32 precision, adds attention …
#hackernews #news #nvidia
A GTX 1660 Ti with 6GB VRAM struggles with modern diffusion models, throwing OOM errors and black image bugs. Instead of upgrading hardware, this build forces FP32 precision, adds attention …
#hackernews #news #nvidia
arXiv:2506.00736v1 Announce Type: new
Abstract: Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in [1/6 of https://arxiv.org/abs/2506.00736v1]
Abstract: Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in [1/6 of https://arxiv.org/abs/2506.00736v1]
June 3, 2025 at 6:01 AM
arXiv:2506.00736v1 Announce Type: new
Abstract: Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in [1/6 of https://arxiv.org/abs/2506.00736v1]
Abstract: Text-to-audio generation synthesizes realistic sounds or music given a natural language prompt. Diffusion-based frameworks, including the Tango and the AudioLDM series, represent the state-of-the-art in [1/6 of https://arxiv.org/abs/2506.00736v1]
AudioSR: 다양한 오디오 신호의 품질 향상 모델 (AudioSR: Versatile Audio Super-resolution at Scale)
(by 9bow님)
https://d.ptln.kr/2893
#musicgen #audiosr #ldm #fastspeech #audioldm #esc-50 #audiostock #vctk #hifigan
(by 9bow님)
https://d.ptln.kr/2893
#musicgen #audiosr #ldm #fastspeech #audioldm #esc-50 #audiostock #vctk #hifigan
AudioSR: 다양한 오디오 신호의 품질 향상 모델 (AudioSR: Versatile Audio Super-resolution at Scale)
이 글은 GPT 모델로 자동 요약한 설명으로, 잘못된 내용이 있을 수 있으니 원문을 참고해주세요! 😄 읽으시면서 어색하거나 잘못된 내용을 발견하시면 덧글로 알려주시기를 부탁드립니다! 🙇 AudioSR: 스케일에서 다재다능한 오디오 슈퍼-레졸루션 (AudioSR: Versatile Audio Super-resolution at Scale) 개요 AudioSR은 낮은 해상도 오디오의 고주파수 구성분을 예측하여 오디오 품질을 향상시키는 방법입니다. 이전 방법들은 처리할 수 있는 오디오 유형(예: 음악, 연설)과 특정 대역폭 설정에 한계가 있었습니다. AudioSR은 음향 효과, 음악, 연설 등 다양한 오디오 유형에 강력한 오디오 슈퍼-레졸루션을 수행할 수 있으며, 모든 입력 오디오 신호를 AudioSR의 대역폭 범위 내에서 업샘플링 할 수 있는 것이 특징입니다. (Any -> 48kHz) 접근 방법 모델 구조 - 고해상도 파형 추정 AudioS...
d.ptln.kr
November 20, 2023 at 9:57 PM
AudioSR: 다양한 오디오 신호의 품질 향상 모델 (AudioSR: Versatile Audio Super-resolution at Scale)
(by 9bow님)
https://d.ptln.kr/2893
#musicgen #audiosr #ldm #fastspeech #audioldm #esc-50 #audiostock #vctk #hifigan
(by 9bow님)
https://d.ptln.kr/2893
#musicgen #audiosr #ldm #fastspeech #audioldm #esc-50 #audiostock #vctk #hifigan
声優Embeddingを計算したいお気持ちになってきた
手持ちの:dlsite:音源をMuLanとかAudioLDMに学習させるやつやってみるか
手持ちの:dlsite:音源をMuLanとかAudioLDMに学習させるやつやってみるか
October 27, 2025 at 9:52 AM
声優Embeddingを計算したいお気持ちになってきた
手持ちの:dlsite:音源をMuLanとかAudioLDMに学習させるやつやってみるか
手持ちの:dlsite:音源をMuLanとかAudioLDMに学習させるやつやってみるか
How to run Stable Diffusion, AnimateDiff, and AudioLDM on a GTX 1660 Ti using FP32 mode, attention slicing, and aggressive VRAM optimization. #generativeaioptimization
How I Built a Full AI Studio for 6GB VRAM Cards (In 9 Hours of AI-Assisted Chaos)
hackernoon.com
March 2, 2026 at 9:05 PM
How to run Stable Diffusion, AnimateDiff, and AudioLDM on a GTX 1660 Ti using FP32 mode, attention slicing, and aggressive VRAM optimization. #generativeaioptimization
I am looking for interactive demos of AI music! It's for an apartment crawl where my apartment has the theme futuristic.
I found AudioLDM but are there other models that I can quickly try?
Or alternatively, any artists/albums where an AI was involved?
I found AudioLDM but are there other models that I can quickly try?
Or alternatively, any artists/albums where an AI was involved?
February 16, 2023 at 3:15 AM
I am looking for interactive demos of AI music! It's for an apartment crawl where my apartment has the theme futuristic.
I found AudioLDM but are there other models that I can quickly try?
Or alternatively, any artists/albums where an AI was involved?
I found AudioLDM but are there other models that I can quickly try?
Or alternatively, any artists/albums where an AI was involved?
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents.
audioldm.github.io
audioldm.github.io
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models - Speech Research
audioldm.github.io
October 20, 2023 at 9:30 AM
AudioLDM: Text-to-Audio Generation with Latent Diffusion Models, a TTA system that is built on a latent space to learn the continuous audio representations from contrastive language-audio pretraining (CLAP) latents.
audioldm.github.io
audioldm.github.io