Tensor.Art
Create

SDXL Yamer's Realism! - Realistic/Anime/3D

CHECKPOINT
Original


Updated:

9.3K

For business inquires, commercial licensing, custom models, and consultation contact me under yamer@rundiffusion.com

Checkpoint Type:SDXL/Realistic/Detailed/High Quality

Follow me on Twitter: @YamerOfficial --- Discord: yamer_ai

If you have enjoyed this checkpoint support me on ko-fi: https://ko-fi.com/yamer

This Checkpoints style is oriented towards images that exhibit a realistic quality, albeit not exclusively centered on achieving a photorealistic appearance. Instead, it emphasizes a realistic semblance while incorporating a 3D style and structural elements within the image. It is particularly well-suited for use in conjunction with my LoRA.

This model is similar to another one of mine: "Yamer's Realistic," it shares similarities with its counterpart, the realism model, both follow the same quality rules.

The Realism models have undergone independent training distinct from the primary Yamer's Realistic models, resulting in divergent training data and distinct output images, the goal of creating realistic images is the same as always.

Take a shot at it and share your thoughts through reviews and comments! I carefully read each comment and genuinely value the support received. A heartfelt thank you to everyone accompanying me on this journey. ๐Ÿ’š

๐•ธ๐–”๐–‰๐–Š๐–‘ ๐•ฝ๐–†๐–™๐–Ž๐–“๐–Œ:

  • Quality: 8.5/10

  • Stability (Variety): 6/10, the lower = the more variety with one prompt

  • Flexibility: 7/10

  • CFG resistance: 25/30

  • Style: 8/10

  • Style Variety: 7/10

แ••( แ› )แ•— Must try with these modifications:

  • LoRA: XL YAMER'S STYLE โ™ ๏ธ Princeps Omnia LoRA

  • 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!

  • Checkpoint tested using: A1111

โ„๐•–๐•”๐• ๐•ž๐•ž๐•–๐•Ÿ๐••๐•–๐•• ๐•ค๐•–๐•ฅ๐•ฅ๐•š๐•Ÿ๐•˜๐•ค ๐•—๐• ๐•ฃ ๐•ฅ๐•™๐•– ๐•”๐•™๐•–๐•”๐•œ๐•ก๐• ๐•š๐•Ÿ๐•ฅ:

Image Quality: 1024x1024(Standard for SDXL), 16:9, 4:3, images in the showcase were created using 576x1024

Steps: 35-150 (under 30 steps some artifact may appear and/or weird saturation, for ex: images may look more gritty and desaturated/lacking quality).

  • Hires Upscaler: 4xUltraSharp

  • Hires upscale: The only limit is your GPU (I upscale 2,5 times the base image, 576x1024)

  • VAE: SDXL VAE

Version Detail

SDXL 1.0

Project Permissions

    Use Permissions

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated images

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.