latent-diffusion VS tortoise-tts

Stable Diffusion XL (SDXL) is the latest text-to-image generation model developed by Stability AI, based on the latent diffusion techniques. SDXL has the potential to create highly realistic images for media, entertainment, education, and industry domains, opening new ways in practical uses of AI imagery.

Here's a link to the early latent-diffusion git, that might be able to create a blank model (I haven't tested it): https://github.com/CompVis/latent-diffusion

Latent diffusion could work for you: https://github.com/CompVis/latent-diffusion (https://arxiv.org/abs/2112.10752)

There are a lot but the one implemented as LDSR in most stable guis is this one. https://github.com/CompVis/latent-diffusion

CompVis/latent-diffusion: High-Resolution Image Synthesis with Latent Diffusion Models (github.com)

The "retrieval based model" refers to https://github.com/CompVis/latent-diffusion#retrieval-augmen..., which uses ScaNN to train a knn embedding searcher.

Stability is basically https://github.com/CompVis/latent-diffusion + training data.

Found relevant code at https://github.com/CompVis/latent-diffusion + all code implementations here

DDIM and PLMS were the original samplers. They were part of Latent Diffusion's repository. They stand for the papers that introduced them, Denoising Diffusion Implicit Models and Pseudo Numerical Methods for Diffusion Models on Manifolds.

yes, https://github.com/CompVis/latent-diffusion

I use Tortoise TTS. It's slow, a little clunky, and sometimes the output gets downright weird. But it's the best quality-oriented TTS I've found that I can run locally.

https://github.com/neonbjb/tortoise-tts

neonbjb/tortoise-tts

EDIT: It appears to be the exact same issue as this

It was primarily being used to train TTS models (see https://github.com/neonbjb/tortoise-tts), which largely fit into a single GPUs memory. So, for data parallelism, x8 PCIe isn't that much of a concern.

Previously TortoiseTTS was associated with PlayHT in some way, although the exact connection is a bit vague [0].

From the descriptions here it sounds a lot like AudioLM / SPEAR TTS / some of Meta's recent multilingual TTS approaches, although those models are not open source, sounds like PlayHT's approach is in a similar spirit. The discussion of "mel tokens" is closer to what I would call the classic TTS pipeline in many ways... PlayHT has generally been kind of closed about what they used, would be interesting to know more.

I assume the key factor here is high quality, emotive audio with good data cleaning processes. Probably not even a lot of data, at least in the scale of "a lot" in speech, e.g. ASR (millions of hours) or TTS (hundreds to thousands). As opposed to some radically new architectural piece never before seen in the literature, there are lots of really nice tools for emotive and expressive TTS buried in recent years of publications.

Tacotron 2 is perfectly capable of this type of stuff as well, as shown by Dessa [1] a few years ago (this writeup is a nice intro to TTS concepts). With the limit largely being, at some point you haven't heard certain phonetic sounds before in a voice, and need to do something to get plausible outcomes for new voices.

[0] Discussion here https://github.com/neonbjb/tortoise-tts/issues/182#issuecomm...

[1] https://medium.com/dessa-news/realtalk-how-it-works-94c1afda...

Tortoise GitHub repo - Source code, documentation, and usage guide

TorToiSe (https://github.com/neonbjb/tortoise-tts) produces the best quality speech of any freely available model. However, its long inference times makes it impractical for voice chatbots like Gdansk.