TL;DR
CinEro Illustrious V5 is a further development of my Pony / Illustrious models designed for better realism and versatility. Highlights:
- High resolution: tested with 1st pass rendering at 1440x768 resolution without high chance to get duplicate elements.
- Enhanced realism: Improved color accuracy, contrast, and sharpness for lifelike images.
- Vintage cinematic aesthetic: Analog film grain, vintage lens blur, and natural imperfections.
- Two versions: FP8 (optimized for RTX GPUs with <12GB VRAM) and FP16 (stable, high-quality CLIP/UNet).
- FP8 performance: Faster inference with minimal resource usage (requires ComfyUI FP8 mode).
- All version have VAE embedded. This VAE is just a standard SDXL VAE with some memory optimizations.
Support the CinEro Project
Training CinEro Illustrious V5 cost me over 10,300 BUZZ, and your support can help fuel future improvements! Here’s how you can contribute:
1. Donate BUZZ: Every contribution goes directly into training the next iteration of CinEro.
2. Spread the word: Share the model on social media, recommend it to friends, and engage with the community.
3. Post your creations: Upload images generated with CinEro, interact with others, and help grow the model’s popularity.
Your time and support are invaluable—whether through BUZZ donations or community engagement, you’re helping shape the future of CinEro!
Recommended Parameters & Tips
[TBD]
Acknowledgments
A huge thank you to everyone who supported previous versions of CinEro through donations, feedback, comments, and sharing their amazing creations. Your contributions have been instrumental in bringing CinEro Illustrious V5 to life.
List of kind supporters:
~={ @belember }=~ ~={@SerLT}=~ ~={@KainKarnage}=~ ~={@Maximo666}=~
@HcupMania @AFD_0 @matrix2014 @AiBan @gman_umscht @HK700 @mphobbit @warlords @namenoname @antigen3 @MysticMindAi @acaciahoney @iheartlumina @jakobhovman259 @funkyflame42513 @Brewce @TheSmokingGPU
@Lizardon1025
Description
FIX 2
Fixes the "Circular Composition" problem (high chance to get a circles dominating the whole composition). V4, V5 BETA, V5 FIX1 - these versions love to render the big circles.
More realistic (dimmed colors, lower contrast), less cinematic relative to FIX1.
FAQ
Comments (9)
Unfortunately needs a face detailer to fix the fugly faces.
Quick release... Let's polish it in FIX 3. Thanks for feedback.
i have v4 i don't get how this devolved. All my faces have weird eyes and it doesn't seem as good as v4. All their faces start looking drawn on
"Drawn on" - you mean smthing is drawn on the face or cartoon like rendering of the faces?
v4 is rly good. v5 cannot hold up in resolutions where i had superb results in v4. so amazing with 3.32gb file size! i love it.
@MJKrakowski Noted... I am working now on new, more clean dataset, to fix the issues reported.
It looks like you’ve regressed a bit on support for gay content between v5 beta and fix2.
I threw together an image with the illustrious versions of your model I had on hand. It shows how things have improved over time with my default fast iteration setup and the abrupt regression to hetero. I spot checked it with a couple of 30 step, lora-free gens, just in case, and included those images.
Hopefully it’s helpful for your next iteration, and thanks for all the great models!
Your observations can be confirmed by the fact that my recent datasets is really aligned to hetero + inter-species interactions + a bit of yuri, but no explicit man-man.
Woman rendered when no 1girl in prompt?
This is bad... CLIP contamination... Thanks for signal. Will think on it.