G-force78
G-force78
> @G-force78 Not sure, depends on what you're using to run the training. But basically, around the part where you save a checkpoint, you need to: > > 1. construct...
> > > > @G-force78 > > Are you having problems or is something not working? That is the correct way to run it. This was because I used 768...
Yes just add --negative-prompt eg: `!aimg edit {enter image path here without brackets eg content/images/initimagename} "prompt goes here" --negative-prompt "negative prompt goes here" --prompt-strength 10 --steps 50` I do wonder...
> > > > Thank you! And maybe you know how to add negative prompt in edit_cli.py? No sorry and that above was for imaginairy they are slightly different
RAM maxxing out here too, on 12gb free collab notebooks.
> > no idea. could be you have too many other things open. could be a bug in the code here. > > > RAM maxxing out here too, on...
Use an old checkout, when i first used it it didnt implement safetensors , which is a nice addition I must say.
> Yes, the hallucination happens as stated in the limitation section of our paper. As the model is based of LLM, it also inherits some limitation of LLM like hallucination...
 Was just about to post that I am not able to select the individual document in the UI, I see you have it on your list to implement. I...
> Hi @G-force78 , yes you can select only an individual document. Just click x near the drop-down icon so All becomes unselected, then select any number of documents, search...