Home » Stable Diffusion
Stable Diffusion: Upscaling methods

Today, I did a few experiments with the upscaling methods. I know at least 3, so let’s look for the configurations and results, and as a summary, let’s select a winner.
Read More »Stable Diffusion: Keywords collection for prompts

I’ve compiled a list of keywords in this post, organized by common characteristics, for different people generation scenarios. These aren’t prompts, but rather words to help you articulate your ideas. You can use it in both positive or…
Read More »Video cards for the Stable Diffusion under 1250 eur/usd

Here is a note about video cards for use with Stable Diffusion and some of their characteristics that need to be taken into account for good generation speed.
Read More »Automatic1111: Prompts for people generation

Today I prepared an article that contains basic prompts that you can use for people generation in Automatic1111 using SD models.
Read More »How to convert Stable Diffusion model from FP16 to FP32

I found that my video card GTX 1660 Super doesn’t fully support FP16 models. So sometimes I need to convert FP16 models to FP32. Here is the python scripts that I usually use for that…
Read More »Stable Diffusion: How to check if a safetensors model file is corrupted

SD models are usually large files, and with a poor internet connection, downloading them can be interrupted and restarted. So it would be helpful if you could validate the model file. Fortunately, this is easy to do.
Read More »Automatic1111: Upscalers errors DAT X2, X3, X4

I face an error when I tried to use DAT upscalers in Automatic1111, that said: TypeError: argument of type ‘NoneType’ is not iterable. I checked what is going on and figured out, so here you can find the…
Read More »