FaserCore is like a digital artist that can do a bit of everything. Whether you're looking to create stunning landscapes, detailed portraits, or imaginative designs, this model is here to help. It’s versatile and easy to work with, making it perfect for any kind of image you want to create. Think of it as your go-to tool for bringing ideas to life, no matter what they are. And as we release newer versions, FaserCore will keep getting better and smarter, handling even more complex tasks with ease.
Important Usage Tips for SDXL Models
Add Stable_Yogis_PDXL_Positives at the beginning of your prompt section.
Add Stable_Yogis_PDXL_Negatives-neg at the beginning of your negative prompt section.
Workflow for Comfy UI
DMD2 Workflow = https://civarchive.com/models/1215102/sdxldmd2workflowbystableyogi
Pro Version of DMD2 Workflow By Stable Yogi= https://www.patreon.com/posts/121447074
I couldn’t have brought this model to life without the invaluable guidance and mentorship of Stable_yogi. He’s been the ultimate master in this craft, sharing insights and techniques that have taken this model to the next level. If you’re looking to create incredible custom models of your own, Stable_yogi is truly the go-to person.
If you have any suggestions or feedback you can always connect with me on civitai chat.
Description
Thanks for your attention , your feedback/review/buzz is much appreciated.
This is a Pony Checkpoint and needs only few steps lie 5 or 6 to create stunning images , it is based on DMD2 Technique.
CFG 1
Steps 5+
Sampler Euler A (Only Euler a or LCM)
And SDXL Size.
Clip skip: 2
Important Usage Tips
Add Stable_Yogis_PDXL_Positives at the beginning of your prompt section.
Add Stable_Yogis_PDXL_Negatives-neg at the beginning of your negative prompt section.
Workflow for Comfy UI
DMD2 Workflow = https://civitai.com/models/1215102/sdxldmd2workflowbystableyogi
Pro Version of DMD2 Workflow = https://www.patreon.com/posts/121447074
FAQ
Comments (17)
follows prompts just nicely and generates a wide range of body types and scenery while being blazingly fast. good job!
Thanks for the feedback. Much appreciated. ❤
Wow... I had to dial down all the CFG and Steps to your sample photo level 1.5 and 10 steps... Super impressed by the realism... has an amateur/Polaroid photo feel to it... very nice and weirdly fast 7 seconds/image on my 3090!! Thanks!
hard to the limmit so you dont can play with steps and cfg ^^
and all images with adetailer - face
This A DMD2 ( Lightning ) Version, works with Low CFG and fewer steps.
@sevenof9247 yes DMD2 Versions can use under CFG 1.5, you can use steps max 10. Above that could give unpredictable results.
@Faser_Media Yeah, I've seen those but I am really impressed with the "look" of the images and the prompt adherence! Well done!! :-D
Wow. Nice model. Very consistent and realistic for Pony. Good job. Waiting for V3_FP32
need this version of FP32 as well.
many thxs in advance
What about a BF16 ?
@Faser_Media For the LORA based on your masterpice, FP32 model could be better, I suppose.
@neoraoz Fp16 is better. I tried but FP32 is not working for me at the moment, i can share BF16 if that works for you.
@Faser_Media OK, I'll try BF16 if you allow me to. THXS much!
Just want to give shoutout for your model for its very high level of detail and consistency. Your model not only works well with LoRAs but also in various sampling settings. It is now my default realism Pony model, and that says something because I have over 20+ pony models in rotation for testing constantly.
Wow !
Thanks a ton, That means a lot. ❤😊
Wow! The most photorealistic Pony model I've seen so far. I am massively impressed, also considering the low step-rate and guidance for a pony.
Thanks for the feedback. The low step version is a DMD2 based model. that's is designed to work with Low CFG and fewer steps.