Problem logging into HuggingFace, and changing output dimensions doesn't work?

[lkewis]

Hey thankyou for this amazing script. I had a problem using 'huggingface-cli login' which wouldn't let me paste my token, but I got around it by changing line 154 of generate_images.py to add my token.

Everything works great but I can't seem to change the output dimensions, it either continues doing 512,512 or has an error about mismatch? (sorry I'm very new to Python scripting, but your video was really helpful)

[lkewis]

Ok the mismatch was because width and height variables weren't being passed into the pipe, which needs to be modified to (GENERATE_DIVERSE)

with autocast(device): image = pipe( # Diffuse magic. prompt, height=height, width=width, num_inference_steps=num_inference_steps, latents=init_latent, guidance_scale=guidance_scale )["sample"][0]

[erickuhn19]

I was also not able to paste my token, what did you change on line 154?

[lkewis]

I was also not able to paste my token, what did you change on line 154?

Hey, on line 154 mine reads: use_auth_token="randomtokenstringhere"