For business inquires, commercial licensing, custom models, and consultation contact me under yamer@rundiffusion.com
Follow me on Twitter: @YamerOfficial Discord: yamer_ai
If you have enjoyed this checkpoint:
Introducing ๐๐๐๐ ๐๐ฎ๐ซ๐๐จ ๐๐๐๐! As an experiment, I've crafted a merged model to explore its potential. Now let's find out if the community prefers SDXL Turbo over the traditional SDXL 1.0. Your feedback is invaluable!
Help the red team by donating buzz and posting images to the model! Be a part of the RED TEAM!
This model is an experiment for the moment, this model hinges on its success and positive reception. If well-received, I plan to consistently enhance it with more content. The primary focus of this model revolves around various forms of art.
I want to say a big thank you to everyone who supports my work by leaving reviews and posting images. Your feedback really helps make the model better, and I truly appreciate every review, image, and comment you share on the models I create.
Restore Face: It is not needed to generate high quality images (Not used in the current showcase.)
Clip skip: 1 and 2 (The model works well with clip skip set to both.)
SDXL Refiner: Not needed with my models!
Quality: 8.5/10
Stability (Variety): 6/10, the lower = the more variety with one prompt
Flexibility: 7.5/10
CFG resistance: 20/30
Style strength: 6/10 (less=more styles)
Style Variety: 8.5/10
No embedding is needed
Faster image generation times!
Better variety of style
No refiner is needed
Less AI generated look to the image. (When creating realistic images for example)
Face fix is not needed
Better saturation, overall quality, texture and tone of the images
Less blurry images and desaturated content
No adetailer required (Just use hires fix)
Image Quality: 1024x1024 (Standard for SDXL), 16:9, 4:3, images in the showcase were created using "576 x 1024"
Hires Upscaler: 4xUltraSharp, 4x_foolhardy_Remacri
Low Steps: 5 to 20 using a CFG between 3 and 7 (Faster images generation = more speed)
High Steps: 20+ use a CFG between 10 and 20 (Images are generated slower)
Hires upscale: The only limit is your GPU (I upscale 2.5 times the base image)
VAE: SDXL VAE
ใใ ๏ผโใฝ
yo. /ยฐ ฯยฐ ใ
ใ ๏ผฟใ ใฝใใ ๏ผผ๏ผฟ โโโโ โโโ
`/ใ`/ โ๏ผนโ ๏ผนใใฝ ใโโโ /โ/
( ใ(ไธใฝไบบใ /ใใ | |๏ฟฃ๏ฟฃ๏ฟฃ๏ฟฃ๏ฟฃ๏ฟฃ๏ฟฃ๏ฟฃ| ใโโโ/โ/
|ใ๏พโ๏ผผ ๏ฟฃ๏ฟฃใฝใ ใ | Send Pizza | ใโโ /โ/โโฌโโโฏ
ใฝ๏ผฟ๏ผฟ๏ผฟ๏ผ๏ฝค๏ผฟ๏ผฟ_๏ผ |๏ผฟ๏ผฟ๏ผฟ๏ผฟ๏ผฟ _____| ใโโโโ|โโโโ
ใใ ๏ฝ( ็ ๏พใ (\__/) || โโดโโดโโ-โโโ
ใใ /๏พ`ใผโๅฝกใฝ (โขใ
โข) || โโโโโโโโโโโฏ
ใใ/ใใฝ_๏ผใ |. / ใ ใฅ โโโโโโโโโโ
| | | | โฏโโโโโโโ