Type | |
Stats | 7,386 3,478 |
Generation | Taking Off |
Reviews | (429) |
Published | Apr 29, 2024 |
Base Model | |
Hash | AutoV2 9356775E08 |
Update June 28th, added V3+VAE, pruned and fp16 versions also added.
V3
More training added to supplement some things I feel are missing in current models. Skin textures, darker lighting and more variety in race in people.
V2
After weeks in the making, I have a much improved model. No longer a merge, but additional training added to supplement some things I feel are missing in current models. Lots of new training for skin textures, lighting and non-asian faces to balance out the asian dominance in models. If you create a generic prompt, you'll get a greater variety of races and faces now. Skin textures are increased by a large amount, if that's not your thing, you can put detailed skin in the negative prompt and get back that airbrushed look if you like.
A photorealistic model I've been using for a little bit. I hate smooth airbrushed skin so I refined this model to be very realistic with great skin texture and details. There are 2 models, a standard and an ultra.
The Ultra model is nearly 3 times as large, but it's not 3 times as good. It is better though with a broader knowledge. You can even generate 1024x1024 in many cases. The config file is required for the Ultra model, be sure to download that too.
So I recommend using the normal version unless you have the need or vram to run the Ultra model. If you'd like to run the Ultra model with modest vram, try --medvram or --lowvram in your auto1111 startup script.
A side-by-side comparison. Link to see full-size samples with metadata. Like I said, the Ultra model isn't 3 times as good, but it is better across multiple subjects, not all. The pruned version of the Ultra model is debatable, might be better to use the normal V1 model in some cases. But all have been provided so you can make the choice yourself. For me, I use the Ultra model in every case.
Do you have requests? I've been putting in many more hours lately with this. That's my problem, not yours. But if you'd like to tip me, buy me a beer. Beer encourages me to ignore work and make AI models instead. Tip and make a request. I'll give it a shot if I can. Here at Ko-Fi
Suggested Resources
Discussion
i think i like the results this one gives better than the absolutereality checkpoint!! nice job
The lack of ethnic variety is a huge issue for the vast majority of checkpoints; so it's awesome you're addressing that! Another problem as I see it-although it's aesthetic- is generations being too warm. This is due to most photos being too warm, thus flavoring the dataset. Would be cool if measures were taken to cool things down a bit for future updates ^_^
This model is just super! Excellent variability, flexibility, attentiveness to even complex prompts, everything is fine!
The only thing I can point out is that the photorealism in the title is a bit unjustified... Yes, it is very close to that. But in order for the model to be very variable, a small piece of photorealism was sacrificed.
Anyway, this is a great model, definitely one of the best of its kind!
Thank you, Zovya!
Excellent model. I like that it had an inpainting version, which is not available for many checkpoints. I'm using the +VAE. Really nice.