--- v3 ---
Improved text handling (still takes a few generations to get it... SDXL... sigh)
Particle improvements (smoke, fire, etc...)
Better animal generations
More Prompt Flexibility with better adherence to age.
--- v2.3 ---
Significant Improvements to Prompt Adherence.
Improved Prompt Flexibility
Better reflections, glare, smoke.
Better multi-character variations.
SPECIAL NOTE: V1.3 has enhanced text generation capabilities. (not perfect, but not bad). v2.3 still has some text abilities but is not as refined as v1.3. I will be releasing a realistic XL base model soon (QuadPipeXL) that will have enhanced text capabilities.
*As always, let me know if you find any bugs and post those photos so I can see how creative you've all been! Thanks everyone!
--- v1.3 ---
I've been asked by a few people why I hadn't released an SDXL model yet. Well it was because I was working on it. This is definitely a version 1. Please notice the sample pictures though, text + sports. Text & Sports are HARD! So this has taken a long time to get to a point where I was comfortable with it.
Flux is still way better at text, but this isn't half bad without LoRAs if you find the sweet spot on prompt and CFG scale.
Anyway, I didn't want to release just another SDXL model... I wanted to move the ball forward a bit. So a few things to keep in mind. The LAION data-tags are relatively preserved. That means that it kind of knows who a lot of people are already, and you won't need as many LoRAs to render notable people and characters.
It does get confused on a few things here and there.
For example, Magic Johnson was number 32 for the Lakers and number 33 for his college team... sometimes it puts the 33 on his Laker uniform. Same for most athletes. This model will try to do text when it can, Mike Tyson is going to have "Tyson" written on his belt etc...
If you don't want text, you're probably going to have to put a negative in. I'm still working on that bit.
As always, thank you for supporting me, and please let me know what you think and if there's something I missed here. I'll definitely be updating this model moving forward.
IMPORTANT NOTE - This model was NOT trained on celebrities, any knowledge it has of celebrities or people alive or dead comes directly from the core SDXL model and the LAION 5B Dataset (which does have a lot of knowledge preserved). All I did here was focus on overall enhancements to fine-tune rendering/lighting/textures/camera positions/objects/emotions, and I did a lot of work on text generation tuning.
Description
FAQ
Comments (7)
It's all fun and games until you realize you have a 48ft cat stuck in your catflap and you can't reach the fridge to make a cheese sammich and your grandma is trapped in the closet next to the kitchen door. It's no laughing matter, I can tell you.
Excellent Model. Thank you... and although it brings back some sad memories, I applaud your superb effort.
Thanks! :)
Just Wow!
It goes head to head with the Epic Realism
I'm glad some people still work on SDXL
Will there be a artwork focused version of Mega Chonk? I'd love to see this immense potential of an engine be more for fantasy, concept art or whimsical artwork
Thank you! I have a few artwork models now, please check out my profile to take a look. It all depends on what style you're looking for I suppose.
For SDXL - focused on artwork/animation/illustration I have the following:
Coffee Rats: https://civitai.com/models/1203288
This one is mostly illustrative with some inspiration from street art and an organic feel.
Blackwing 602: https://civitai.com/models/913338
This one is focused on Pencil Sketch - it does black and white, and color sketching.
Pulp Fantasy: https://civitai.com/models/574186
This one is inspired by the old Pulp Sci-Fi comic book covers. It's a little more flexible and doesn't hold too frantically to that style. It's a little muted, and vintage feeling.
I have another SDXL model focused on artwork that I'm working on right now, but it'll be a week or so before I release that one. I've been working on it to achieve a very specific style of illustration/animation.
re: SDXL. Right now I think SDXL is the most flexible when it comes to licensing and with the right models you can get really really close to FLUX outputs. The prompts aren't as flexible as FLUX - but it leaves more room to explore. I am working on SD3.5 models right now as well, but I won't release those until there's an easy and mainstream way (A1111 or Forge) for users to deploy them. I don't think ComfyUI is easy enough for the majority of users right now.
@QuadPipe thanks for the reply! Yeah, your other models are not my taste, they are very Euler-ish which I heavily dislike, haha
Not to disregard their individual qualities, they are very trippy though, but not suitable for that "artwork" feel
@PrecisionMaster - definitely not for everyone. The next illustrative one I have is a little more friendly to DPM++ 2M SDE / Karras
I wanted to make a higher-step, refined illustrative model. Stay tuned, maybe that one will be something that you find use from. Either way... thank you for the kind words!! :)
@QuadPipe 💪🏽