<h1 id="heading-3293">JV-MIX (MERGE)</h1>VERSION 2.0 Revison 1: New Models, Improved Generations. Different Sampling settings(TESTED and CONFIRMED): This model works wonderfully with the LCM Sampler and LCM Lora. Make sure when using the LCM Sampler that you have your steps set to at a minimum of 6.<h3 id="heading-3294">Merge of 3 Checkpoints:</h3><ul><li>MIX-Pro-Remaster (629f56d8d5)</li><li>Sudachi (9b170ebadc)</li><li>tmndMix-VII (e16273c410)</li></ul><h3 id="heading-3295">Model Parameters:</h3><ul><li>Sampler: DPM++ 2M SDE Karras or any other DPM model (Except 3M)</li><li>Sampling Steps: 20 - 40 (30 Recommended)</li><li>Hires. Fix: Enabled</li><li>Upscaler: 4x-UltraSharp or 4x-AnimeSharp</li><li>Hires Steps: 15</li><li>Denoising Strength: 0.4</li><li>Clip Skip: 2</li><li>VAE: <a target="_blank" rel="ugc" href="https://huggingface.co/MoistMix/MoistMixV2/blob/main/MoistMixV2.vae.pt">MoistMix</a></li></ul><h3 id="heading-3296">Recommended Textual Inversions:</h3><ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/11772/verybadimagenegative">veryBadImageNegative</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/56519/negativehand-negative-embedding">Negative-hand</a></li></ul><h2 id="heading-3297">PLEASE DON'T USE ANY OF THE MODELS I HAVE MERGED OR CREATED FOR COMMERCIAL PURPOSES</h2>If you have any questions feel free to comment

JV-MIX

Added tmnd-mix as tertiary model, weighting throughout each model: 0.4.Added Sudachi as secondary model.Removed Mix-REV4.Supports Inpainting, Img2ImgBest ever lora support

Files with SHA256: 27feddeb5e373123524bace53aab7595a3118a4d2fcbec1e67985a60fa3015cf