I've made some significant updates to the LusciousMix latest version of the model in order to add more diversity and improve the overall quality of the generated photos. Even though I've introduced more variety, rest assured that this version is still capable of generating stylized or semi-realistic photos like the previous version.
I'm excited to share that this version also excels at the Euler A sampler and DPM++ 2. However, please keep in mind that this is still an experimental version, and I'm working hard to continue improving it.
Your feedback is valuable to me, so please don't hesitate to share your thoughts on this version so I can improve future iterations. Thank you!
Description
Currently, the model is in version 1.0, but please note that this is still an early version based on a variety of experiments. I am constantly gathering feedback and improving the model to make it even better.
As I continue to experiment and refine my approach, I'm excited to see where the model will go in the future. So, if you try out the current version, please let me know your thoughts and any suggestions you may have - I'm always eager to hear from the community and improve my work!
FAQ
Comments (7)
Seems pretty good in semi-realism and could certainly get better in realism.
Btw, can you add a smaller 2gb pruned-fp16 version (without baked vae) ?
Well, your request is very specific "2gb pruned-fp16 version (without baked vae)" can you please tell me why you want the pruned version is this because of the disk space or do you want to use your own vac? Don't worry, I can give you what you asked for. Just give me some time. I'm not sure about the quality though!
Hey there! I just uploaded the pruned version of the model, and I'm hoping you'll enjoy using it as much as I enjoyed working on it. If you get a chance to try it out, please do share your results with me! I'd love to see what you come up with and get a sense of how the model is performing in the wild.
Additionally, if you have any preview images you'd like to share, I'd be more than happy to take a look and use them to improve the next version of the model. Thanks for showing interest in my work.
@Patchmonk Thanks. Most published models here, are already pruned-fp16 or even smaller LORAs, and of course there is a little price to pay in reduced quality. I'm collecting hundreds of good models and I prefer to maintain the filesize at 2-3gb max. At the moment I can't produce my renders for hardware limitations, just collecting for now. Thanks again.
@ritcher1 No problem at all! I'm really glad to have had the opportunity to share some of my work with this community. It's such a wonderful place, and I feel so grateful that we have access to so many amazing models, thanks to the contributions of so many talented people.
I'm excited to continue contributing to the community and see what we can create together. Thanks for being a part of this journey!
The model is hugging face?
I use Google colab to run stable diffusion xd
No, I didn't upload this model on hugging face, if you want you can always use it on google chrome. Good luck!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.