EMA produces sharper images while MSE's images are smoother____________________________________________________________________________Sharing this model with the community. As it closely resembles Lexica Art V2 or Lexica Aperture v2, this product is an excellent choice.It's absolutely amazing how we're able to create incredibly realistic faces with only a few simple steps. If you want to support my work, you can buy me a coffee or tea:<a target="_blank" rel="ugc" href="https://ko-fi.com/gswan">https://ko-fi.com/gswan</a><a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/gswan">https://www.buymeacoffee.com/gswan</a>Enhance your writing prompt by adding the <code>estilovintedois</code> prefix, as it guarantees a consistent writing style."While you're welcome to use this model, please keep in mind that any potential damages or mishaps resulting from its use are not our responsibility..." "This model was trained on a large amount of high quality images with simple prompts to generate beautiful images without a lot of prompt engineering.""It should also be very dreamboothable, being able to generate high fidelity faces with a little amount of steps." This model is based on vintedois_diffusion. Credit to the original developers. Vintedois (22h) Diffusion model trained by <a target="_blank" rel="ugc" href="https://twitter.com/Predogl">Predogl</a> and <a target="_blank" rel="ugc" href="https://twitter.com/piesposi_to">piEsposito</a> with open weights, configs and prompts (as it should be). Example prompts<ul><li>Prompt: photo of an old man in a jungle, looking at the camera</li><li>CFG Scale: 7.5</li><li>Scheduler: <code>diffusers.EulerAncestralDiscreteScheduler</code></li><li>Steps: 30</li><li>Seed: 44 Prompt: kneeling cat knight, portrait, finely detailed armor, intricate design, silver, silk, cinematic lighting, 4k</li><li>CFG Scale: 7.5</li><li>Scheduler: <code>diffusers.EulerAncestralDiscreteScheduler</code></li><li>Steps: 50</li><li>Seed: 44</li></ul><ul><li>Prompt: a beautiful girl In front of the cabin, the country, by Artgerm Lau and Krenz Cushart，hyperdetailed, trending on artstation, trending on deviantart</li><li>CFG Scale: 7.5</li><li>Scheduler: <code>diffusers.EulerAncestralDiscreteScheduler</code></li><li>Steps: 50</li><li>Seed: 44</li><li></li></ul><ul><li>Prompt: destroyed city</li><li>CFG Scale: 7.5</li><li>Scheduler: <code>diffusers.EulerAncestralDiscreteScheduler</code></li><li>Steps: 50</li><li>Seed: 44</li></ul><ul><li>Prompt: victorian city landscape</li><li>CFG Scale: 7.5</li><li>Scheduler: <code>diffusers.EulerAncestralDiscreteScheduler</code></li><li>Steps: 50</li><li>Seed: 44</li></ul><ul><li>Prompt: prehistoric native living room</li><li>CFG Scale: 7.5</li><li>Scheduler: <code>diffusers.EulerAncestralDiscreteScheduler</code></li><li>Steps: 50</li><li>Seed: 44</li></ul>

LexArtDiffuzeX

Baked in VAE MSE. It helps render eyes and text where all fine details matter. MSE’s images are smoother.

Files with SHA256: b86005739831b97dc51e7c3c48f76a493a83d765589a3d1954d979a66aa169db