What’s the difference between SDXL and SD1.5 in terms of difficulty promoting? Im trying my hand at making a couple gens again, should I forget my old models and move to the XL model?
SDXL moves from a base resolution of 512x512 to 1024x1024 along with better prompt recognition, so your prompting will likely need to evolve. However, there is a new type of SDXL model, ‘lightning’ that generates images in 2-8 iterations as opposed to 16-60. Prompts are also different for these types of models. I suggest the SDXL Lightning version of Juggernaut. The only time you might be interested in going back to older models would be compatibility with Loras or animation modules.
Note that on lightning models you’ll need to lower your CFG Scale to around 1.5 - 2.5
What’s the difference between SDXL and SD1.5 in terms of difficulty promoting? Im trying my hand at making a couple gens again, should I forget my old models and move to the XL model?
SDXL moves from a base resolution of 512x512 to 1024x1024 along with better prompt recognition, so your prompting will likely need to evolve. However, there is a new type of SDXL model, ‘lightning’ that generates images in 2-8 iterations as opposed to 16-60. Prompts are also different for these types of models. I suggest the SDXL Lightning version of Juggernaut. The only time you might be interested in going back to older models would be compatibility with Loras or animation modules.
Note that on lightning models you’ll need to lower your CFG Scale to around 1.5 - 2.5
https://civitai.com/models/133005/juggernaut-xl
Yeah, I do like using a lot of specific Lora’s. I’ll download XL today though, see what it can do