Stable diffusion model of the text2image generator
Stable diffusion model of the text2image generator
Hi, I would like to know what model for stable diffusion the Perchance text2image generator use. I am not able to have the same (very good) results "at home" with the basic model or custom ones so it's seems it's a specific one ? I would like to try adding some LoRa. So It will help me to have the name of the model, or if it's a custom one could you share it ?
Hi, check out this post regarding the model.
thank you ! well I think my problem is the "art style" settings of the perchance generators that I don't replicate with the right prompts/tags. maybe it is because I use "easy diffusion 3" and not automatic1111 ? is all the exact same "art styles" on automatic1111" too ? I use easy diffusion because it was way easier to install ^^ because for now I just can't replicate the results of the generator on easy diffusion while using the exact same prompts and settings (mainly guidance scale), the only thing which is not the same is the "art style", on easy diffusion they are "Image Modifiers" but they are not the same at all. Or if the "art style" are specific to the prechance generator, it could helps a lot to know what each of them add to the prompt text
If you mean about the 'styles' on
ai-text-to-image-generator, their styles can be found on this styles page which is imported on the main page.Also, I really would suggest making your own text-to-image generator so you can customize it with full control to the tags/negative prompts. The general image generator is good, but you can have more control/fine tuning if you create your own.
We have a guide to prompting to get you started on creating your own text to image and if you have trouble in fine-tuning the images you want.