itch.io

Indeed, the first link is incorrect; I confused it with this one: https://civitai.com/models/2642635/minimal-techno-overdrive-lora-ace-step-v15-xl-base  But it requires a 12GB card.

The idea is to use existing LoRa modules because, on smaller systems, this would allow us to add a specific LoRa module to the basic model, depending on the style of music we want to generate. For example, we should normally be able to use this: https://civitai.com/models/2425543/ace-step-15-music-generation-for-low-vram
 or https://civitai.com/models/2624128/ace-step-15-psytrance-lora-ver-20... Indeed, there's an option to create your own LoRA modules in an hour with a simple setup, as described here: https://github.com/ace-step/ACE-Step-1.5/blob/main/docs/en/LoRA_Training_Tutorial.md This is definitely an option that could be of interest to other users of your application.

Is it possible to add LORA elements to have, for example, a more specific Cuban style, piano music, or even French pop music from the 80s?

I have an 8GB card, so I won't have the chance to discover these new models. Thanks anyway for the new features.

I can't figure out how to add the XL Models. I thought I'd find them by clicking the configure button in the Model Assignment, but they don't appear in the lists. What should I do? (I'm using version 1.3)

I can't figure out how to add the XL Models. I thought I'd find them by clicking the configure button in the Model Assignment, but they don't appear in the lists. What should I do? (I'm using version 1.3)

This application is very well designed for those who don't know how to install FaceFusion or who prefer simplicity. And if GIF format support is added in the future, it will be a real added value, as FaceFusion users currently have to convert GIFs to videos to swap them.

Thank you for your feedback. The ability to extract and add instruments is indeed interesting, and perhaps the option to retrieve the different tracks separately would be beneficial. Something to keep an eye on.

Generations are finally working with the new update, however the quality of the generations is identical to the free tool available on pinokio in one click : https://github.com/BazedFrog/SongGeneration-Studio

What's the point of paying for something that doesn't add value? Are there other options planned to improve the experience?

In Rover:  The Express server serves static files.  But for Unity, you need to check:  MIME headers  .wasm support. Therefore, I think you should add the following to the server script:const express = require('express'); const path = require('path');  const app = express(); const PORT = 3000;  const contentPath = path.join(__dirname, 'content');  app.use(express.static(contentPath, {   setHeaders: (res, filePath) => {      // WebAssembly (OBLIGATOIRE)     if (filePath.endsWith('.wasm')) {       res.setHeader('Content-Type', 'application/wasm');     }      // Unity data files     if (filePath.endsWith('.data')) {       res.setHeader('Content-Type', 'application/octet-stream');     }      // Disable cache (debug friendly)     res.setHeader('Cache-Control', 'no-store');   } }));  app.listen(PORT, '127.0.0.1', () => {   console.log(`Unity WebGL server running at http://127.0.0.1:${PORT}`); });  module.exports = PORT;

I reported the problem in the comments of the page: https://ryanbram.itch.io/valet-lightweight-local-web-server-and-browser-launcher

Hello,  I tested your application to see if it could run an HTML5 game created with Unity. Unfortunately, the framework.js script is compressed, and when I run your application, I get an error message. Apparently, the web server hosting the content is misconfigured and isn't serving the file when the HTTP response header is "Content-Encoding: gz".The solution is clearly at this address:https://docs.unity3d.com/2020.1/Documentation/Manual/webgl-server-configuration-code-samples.html . Your project might not be to extend compatibility to games created with Unity in HTML5, but I think it would be a good idea ;)

Interesting program but not open enough. Being able to import textures will be an improvement but for me the most important thing would be to be able to select the animations before generating the character. Indeed, for the moment all animations are added by default which makes the 3D model heavier. Moreover, for optimized low poly only the layers used should generate polygons (currently all layers are generated even if they are not associated with any texture... Once again this makes the 3D model heavier). But nevertheless congratulations for this very promising program

Ok I just posted a message on your Twitter account

Hello, i haven't got Paypal, is there an other way to buy your app (credit card or steam...) ?