(More photos below had issues arranging them properly for V2)
( And please feel free to upload your creations with this model I know I and the community love to see what you come up with 😄 )
Edit for V2*
I focused on getting this one to be more detailed with skin and more flexible in general. Each model revision has its strong suits and weaknesses. This one had issues with hands sometimes but has great quality in other areas like textures etc. I wish I could make one model to rule them all but sadly thar seems impossible at this time due to the limited model size etc... Maybe FLUX will bridge the gap? Who knows but if you don't enjoy this model try an older revision or don't it's up to you but I appriciate everyone's feedback, you guys are the main reason I do this and I hope I didn't disappoint with this new revision. Sadly it's only an FP16 model the fp32 got lost at some point in translation but shouldn't be a biggie. Again thank you all and this may be my last model for a while until I can get some newer hardware to train on. I would never expect it but If anyone feels like helping fund that shoot me a message! Thank ya'll again!
edit for V1*
Here it is, finally out of beta and I am extremely pleased with the results. This updated model offers greater versatility while continuing to prioritize realism. While primarily designed for 512x512 images, it can also handle 1024x1024 images with some trial and error depending on the complexity of the prompt and settings.
This model is compatible with LCM and can be paired with SD Turbo, though it may not be the best option for high quality images, it is great for rough drafts. Feel free to experiment with the settings and let me know your feedback!
I also included both fp16 and fp32 versions of the model.
For creating 1024x1024 images, I personally recommend using DPM++ 3M SDE GPU for the sampler and Karras for the scheduler, with 50 steps and HiRes fix enabled. If you are interested in my exact settings for this, feel free to ask!
Lastly, please share images of your creations - I would love to see them! 😀
* For V.05 - Beta
--------------
I've been working on this model for a while and figured I'd release a Beta of it. It still has a long way to go but has potential. Please upload pics you made with it so I can see what needs to be improved. So far this model focuses on skin textures and lifelike realisum. It can do NSFW and yes... It can kinda do buttholes which I know most models struggle with hah! If anyone has any questions dont hesitate to reach out :)
I personally use:
DPM++ 3M SDE GPU for the sampler
And Karra's for the Scheduler.
Steps normally around 40 and CFG scale you can play with a lot on this model, sometimes 1.00 works sometimes 5 works better.
I normally have mine around 2.75-4.00
Again its a beta so let me know!
Description
Here Is Almost Anything V2.0! I tried to make it more flexible and more focused on skin textures. Im having to rush writing this as I have other things I need to get done today and just wanted to release it. I will write a more in-depth change log later but give it a shot if you will and let me know what you think! :D
As aways thank you all for your support!
FAQ
Comments (11)
That looks spectacular 🤩
Thank you so much!! 😄
@AnomalousConcepts You’re welcome ❤️
It works fine without a GPU. I have a CPU only system with 64 GB of RAM. So far I'm liking the model. I had been using my own model for a while, this might be my new daily driver.
Dang!! I'm glad you like it!! I've never used it with just a CPU, how long roughly does it take for an image output if you don't mind me asking. I honestly didn't even know you could even run it on a straight CPU. I have an RTX 3080 Ti and it still struggles 😅
@AnomalousConcepts I just generated an image of a woman in a black swimsuit in 2m37s. I'll post it so you can see it.
@jcm4atx Dang, 2ish-mins isn't bad at all for CPU only. I actually got it setup on my friends computer that doesn't have a video card due to your comment. It takes them closer to 30 mins but it's kinda a basic office computer so im just surprised it works at all. Thank you for letting me know!! Now they can generate images. Obviously it takes forever but atleast it's possible 😄
I have to say that 1.0 has been my go-to for when I wish to create close-to-real fantasy and science fiction scenes. None of the other models (i use about 30 others ) come close to this checkpoint.
It is also superb with realistic people. If I had to choose only 3 checkpoints to last me the rest of my time v1.0 would be one of them.
I look forward to trying out 2.0 ! Thanks so much for making this available friend.
Thank you so much!! I tried to make it as lifelike as possible while still being able to do other styles. I'd love to hear your feedback about the other versions. If you have time don't hesitate to try the beta too! They are all different in their own ways. I just can't seem to pack them all into one model which is the most frustrating part. With SD you can only get so far then you start getting limited with how much info you can pack into a model. Right now I'm very limited with what I can do with my hardware when it comes to say Flux, etc.. so ima have to wait a while to upgrade my system to get into training that 😅 but anyways I'm super glad you like it!! Keep me posted if you try the other revisions 😄
sick model !!!!
Thank you so much!! 😄😜
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.