You can try using a blowjob lora.
It doesn't matter how slick your prompt is if the checkpoint isn't trained to do what you're asking it to do...
Any instructions on how to use it? These aren't .cpkt files what to do with them?
Sad to say, no yet. My machine is an Intel i3 16G Ram with an 4G GFX card, relic from the XX century :'(
So how to use it?
I'm assuming you're using A1111 or SD Webui which have basically the same working gui. Select the model you want as the base (.ckpt or >1.8GB .safetensors) from the drop down at top left e.g. UberRealisticPornMerge.
I use Easy Diffusion v2.5.22
I recommend following this tutorial video and ditch this easy diffusion, it looks rather limited and it will only make it more difficult for anyone to help you since most people use either Automatic1111 or SD web Ui.I use Easy Diffusion v2.5.22
You must be registered to see the links
I did not know there are other versions.
So I followed your guide, created new folders:
W:\stable-diffusion-ui\embeddings [mjv4Hypernetwork_v1 - 112 mb .pt file]
W:\stable-diffusion-ui\models\Lora [hipoly3DModelLora_v10 + samdoesartsSamYang_offsetRightFilesize]
W:\stable-diffusion-ui\models\stable-diffusion [neverendingDreamNED_bakedVae.safetensors]
But I see no picture icon under generate button to set this up embeddings and LORA?
Could you please explain why there are different versions of the same model? I saw these:
-float16.ckpt
-float32.ckpt
-full.ckpt
-opt.ckpt
Is it not better that you learn to do it yourself? What happens next time you want to fix an image?
I have seen many people getting it to work with potato pc's. There are solutions for any cuda memory error you might encounter because the low vram. This article links to a fork for low vram users.Sad to say, no yet. My machine is an Intel i3 16G Ram with an 4G GFX card, relic from the XX century :'(
I'm planning to get a better one. maybe this year
The different models are dependent upon specific needs or limitations.I use Easy Diffusion v2.5.22
You must be registered to see the links
I did not know there are other versions.
So I followed your guide, created new folders:
W:\stable-diffusion-ui\embeddings [mjv4Hypernetwork_v1 - 112 mb .pt file]
W:\stable-diffusion-ui\models\Lora [hipoly3DModelLora_v10 + samdoesartsSamYang_offsetRightFilesize]
W:\stable-diffusion-ui\models\stable-diffusion [neverendingDreamNED_bakedVae.safetensors]
But I see no picture icon under generate button to set this up embeddings and LORA?
Could you please explain why there are different versions of the same model? I saw these:
-float16.ckpt
-float32.ckpt
-full.ckpt
-opt.ckpt
The easier faster thing would be to try one of the free online generators.Sad to say, no yet. My machine is an Intel i3 16G Ram with an 4G GFX card, relic from the XX century :'(
I'm planning to get a better one. maybe this year
I don't get it
Just follow this video and install Automatic1111, it's only different user interfaces so you don't loose anything by choosing this over the other. In fact just forget about any other UI for now.
OK, BUT!Just follow this video and install Automatic1111, it's only different user interfaces so you don't loose anything by choosing this over the other. In fact just forget about any other UI for now.
In the video he show you how to install and use a basic version of Stable diffusion 1.5 .
Stable Diffusion 1.5 or 2.1 is the actual "models", then you go to civitai.com and get a trained checkpoint or merged checkpoint.
This is stable diffusion 1.5 that has been trained for specific genre's and niche's. This is what you use as a "generator".
Then you can add other things like lora's for a more "controlled" result. Stable Diffusion 2.1 is not NSFW content for now as far as I know so not interesting to us perverts..
