About this version:
Improvements overall and fix for the problem reported with overfitting and loss of prompt following in the previous version.
Recomendations:
Default SD 1.5: Use the "DPM++ SDE Karras" or "DPM++ 2M Karras" sampler with only 20 steps for better quality. "DPM++ SDE Karras" has better quality but is slow.
Default SD 1.5: Use the CFG scale between 5 and 9. CFG scale at 5 is recommended. Stable Diffusion default value is 7.
SD 1.5: Resolution between 512 and 768 using "Hires. Fix" or other form of upscaling. The 600x600 resolution is the one that has worked best.
SD 1.5 LCM: Use the "Euler a" or "LCM" sampler with only 8 steps for better quality.
SD 1.5 LCM AND SDXL Lightning: Use the CFG scale between 1 and 2. CFG scale at 2 is recommended.
Pony SDXL: Use the "Euler a" or "DPM++ SDE Karras" sampler with 20-30 steps for better quality.
Flux 1 Dev: Use the "Euler" sampler, "simple" scheduler, distilled cfg 3,5 and 20 steps.
If you use "Hires. Fix", use "Upscale by" with the value 1.5 with denoising at 0.6.
Tips for a better prompt:
Use (word) for larger weight and [word] for smaller weight and (word:0.5) to set the weight manually.
Recomendations for improvement on performance (Stable Diffusion Web UI):
Use Token Merging Ratio 0.5 on optimization settings.
If you have a GPU with low VRAM, use --medvram or --lowvram on command line arguments (webui-user.bat on Windows).
Enable fp8 in the latest versions of Web UI to save a lot of ram. It can speed up SDXL a lot depending on how much ram and vram you have.
If you are having a lot of trouble running SDXL in the Web UI. Try using Fooocus
Extensions I recommend: Controlnet, Booru tag autocompletion, CivitAI Browser+,Ultimate SD Upscale,Lobe Theme
Recommended negative prompts to improve human images: amputee, deformed body, long neck, extra fingers, bad body proportions, mutated hands, mutilated, mutation, ugly, fused fingers, malformed limbs, extra heads, disfigured,
I would like to thank the following projects that were important to the community and helped improve Stable Diffusion to achieve greater levels of realism:
Realistic Vision
RealVisXL
epiCRealism
epiCPhotoGasm
QGO
ICBINP
Analog Madness
majicMIX realistic
CyberRealistic
Juggernaut
LCM Lora
SDXL Lightning
Fast Pony Merge
Real Pony
Pony Realism
Osorubeshi Pony
Sevenof9 Pony
Sat Pony
Stallion Pony
Special thanks to other projects from anime and artistic models:
Pony Diffusion
AutismMix SDXL
T-ponynai3
Prefect Pony XL
This is not my model, i take no credit for it. all credit goes to the creator @ https://civitai.com/models/153568/real-dream