Get the pro version of my checkpoints and workflows. Get the Pro version of my models here.
Onsite generations are permanently available on these models:
👉 Realism_Illustrious_By_Stable_Yogi : https://civarchive.com/models/974693?modelVersionId=2091367
Read "About this version" Section for Model details and settings.
Important Usage Tips to get similar results like my images.
Add Realism_Illustrious_Negative_Embedding at the beginning of your negative prompt.
Add Realism_Illustrious_Positive_Embedding at the beginning of your prompt.
Loving this model? Get the Pro version of my models herefor exclusive perks and early access to unique resources.
To discuss custom Lora's or models, feel free to connect on Discord.
đź‘Ť Like this model to keep me motivated and inspired to create more!
đź’¬ Drop a comment and let me know what you'd love to see next.
🌟 Review this model to help me improve and make even better creations.
đź”” Hit that notification bell to stay updated with my latest models and updates!
Description
V5.5 Refinement Update:
Improved prompt adherence for clothing details, garment types and color accuracy
Better pose interpretation — sitting, standing, reclining and dynamic poses render more consistently
Refined hand anatomy with improved finger definition and object interaction
Enhanced multi-figure composition and spatial relationships
Stronger facial detail retention in full-body and mid-range shots
Overall aesthetic polish with maintained realism and lighting quality
What's unchanged:
Same great skin textures, lighting and style range from V5
Fully compatible with existing workflows and LoRAs
Recommended Samplers:
DPM SDE , Euler A,
Optimal Settings:
Steps: 27+
CFG Scale: 5
Clip Skip: 2
Resolution: Any SDXL resolution, 896x1152
Loving this model?Get the Pro version of my models here for exclusive perks and early access to unique resources.
FAQ
Comments (18)
Could you please put the BF16 on Patreon please?
Sure
Uploaded.
Just want to say, you are a beautiful, brilliant genius.
These models are INSANE.
What does the trigger "99bsy99," do for the image?
It triggers some concepts used in training.
@Stable_Yogi can you tell me about some of the concepts? I'm just curious.
Great on the update. AI still has its issues with teeth or aleast when I try to add a character lora into the mix.
Appreciate the feedback — it genuinely helps improve everything we build.
I’ve set up a proper feedback system now. If you’re down, hop into Discord, try the upcoming models, and share what you think.
You’ll be helping shape better models going forward 👀
Before I start pointing out how dumb I am... Excellent model at least in my workflow.
Anyway so I was siting for at least 45 minutes "switching" schedulers and samplers trying to swtich off and on node I use to generate better images... and you know what it was... I use using the scheduler and and sampler setting in the USDU node when I have them overridden by other node, blanked them out now... but... FRICK!!! Was gonna come in here saying the model sucks for up scaling but creates great (for SDXL) initial images... So glad I decided to do more testing before I said anything.
is it suit for my 3060ti laptop(6gb VRAM)?
Yes it should work, try with Forge Neo.
@Stable_Yogi thanks
I really like your work. Have you ever thought about doing a Chroma1-HD fine-tune as the realism is great and it's pretty much uncensored out the box. They do also have Chroma Flash DMD2 LORAs to. I think rank 256 and 128 are great.
Thank you !
I haven't yet, i will try it, thanks.
@Stable_Yogi that would be awesome! chroma is a beast for uncensored out of the box. you just need to prompt it correctly which most people fail to do. think of the positive and negative prompts as a see-saw. they balance each other out. or cancel each other out i should say. write in complete sentences for both pos and neg. for example: if you don't want "sun and mountains" in your image, then prompt "its a sunny day with mountains in the background" for the neg. and so forth.. its a fun model once you understand its prompting.
I like this model, it does good backdrops for my projects. Euler A + Beta works the best for this checkpoint.
I have problems generating anal sex images can anybody help? Thanks in advance.