jepjoo
jepjoo
It's supported already. 1. tick Advanced 2. Advanced tab, top right corner 3. tick developer debug mode 4. Scheduler -> turbo 5. Forced sampling steps -> 1-4 6. Forced resolution...
Correct. If stop at is 0.5, the image prompt will only be in effect for the first half on generation.
This sort of functionality was just added 10h ago. Your log files will now have a button to copy settings of a previously generated image into clipboard and you can...
Looks like it's for SD 1.5 though. No mention of XL in the model card.
I was thinking exactly the same as I've been playing with the awesome Slider LoRAs. Here's a good example from camenduru of how going beyond weight of 2 can be...
Okay, found a very simple hack for this. Just tried it with the age lora and it works: Open webui.py, change values on line 302: lora_weight = gr.Slider(label='Weight', minimum=-4, maximum=4,...
I had this error on first boot after update (I had some weird Windows "let's finish setting up Windows" screen pop up on install even though my installation is about...
If, I'm understanding correctly, it looks like that functionality is removed: "You now need to enable multiple IP-Adapter units to achieve effect of previous multi-inputs" https://github.com/lllyasviel/stable-diffusion-webui-forge/discussions/40
> The multiple-inputs tab is removed. The batch tab is not removed. Hmm... not sure I follow. Batch tab is not removed, correct, but it isn't really working as only...
Int8 and int4 models are available now too. https://huggingface.co/fnlp