Get the pro version of my checkpoints and workflows on my Patreon.
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.
Join me on my Patreon for exclusive perks and early access to unique resources.
To discuss custom Lora's or models, feel free to connect on Discord.
👍 Like this model to keep me motivated and inspired to create more!
💬 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.
🔔 Hit that notification bell to stay updated with my latest models and updates!
Description
Recommended Samplers:
Euler A , DPM++ SDE - SGM Uniform
Optimal Settings:
Steps: 27+
CFG Scale: 5
Clip Skip: 2
Resolution: Any SDXL resolution
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.
Join me on my Patreon for exclusive perks and early access to unique resources.
FAQ
Comments (8)
What are the differences between your three realistic illustrious models?
Realism_Illustrious: https://civitai.com/models/974693?modelVersionId=1372996
Babes_Illustrious: https://civitai.com/models/1134825?modelVersionId=1393867
Porny_Illustrious: https://civitai.com/models/1135451/pornyillustriousbystableyogi
Their focus is different.
realism = overall realism
Babes = female focus,like insta type images
Porny = biased towards nsfw.
@Stable_Yogi Thank you
All the nipples are the same! I can't stop seeing it.
I appreciate your pin point focus on "nipples" 😁
v3.0_DMD2 is quite impressive. Converted to TensorRT I'm generating images on a 4090 in ~4 seconds at a 1248x1824 resolution with a simple latent hires fix workflow using Euler a, CFG 2.0, 8 steps each. Gens look better / more realistic compared to non DMD2 checkpoints at the same resolution which take ~15-20 seconds.
With Illustrious as the base the prompt comprehension (with danbooru tags) is pretty good - imo better than any pony based realistic model I've tried.
It would be interesting to see a NoobAI epsilon 1.1 as the base for this fine-tune 🤔
hey, thx for comment. Whats the difference between dm2 and fp16? i know that last one affect memory usage twice as low as regular 32. but what is dm2?
@digitalego You can read the abstract here: https://arxiv.org/abs/2405.14867