I was generating images today with this AI when I wanted to see the results it's just black pictures, when I came back here and read the "Important Stuff" section the first line that was written is about GTX 1660 cards not being able to render and unfortunately my card is a GTX 1660 Super so I guess i was unlucky.
can someone explain how to actually paint/mark areas with inpaint? i choose a input and i choose inpaint model, what am i missing after that? all it does is render a new image.
I ran into an issue where I can run a prompt at 100, 200, 400 and 500 iterations, but 300 iterations gives an error: Rendering: anime screenshot wide-shot landscape with house in the apple garden, beautiful ambiance, golden hour
0it [00:00, ?it/s]
Traceback (most recent call last):
File "start.py", line 363, in OnRender
File "torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "diffusers\pipelines\stable_diffusion\pipeline_stable_diffusion.py", line 152, in __call__
File "diffusers\schedulers\scheduling_pndm.py", line 136, in step
File "diffusers\schedulers\scheduling_pndm.py", line 212, in step_plms
File "diffusers\schedulers\scheduling_pndm.py", line 230, in _get_prev_sample
IndexError: index 1000 is out of bounds for dimension 0 with size 1000
V Scale is 7.50, resolution is 768x512, seed: 12345, on a 3080 12GB.
← Return to tool
Comments
Log in with itch.io to leave a comment.
My video card is missing cuda divice, gpu 3070, only the cpu remains, sd gui 1.8.0
then error on startup (Detected no CUDA-capable GPUs.)
What version of stable diffusion does the Grisk Stable Diffusion GUI 0.1 run?
Does anyone know what is the default Sampling method in GRisk?
I was generating images today with this AI when I wanted to see the results it's just black pictures, when I came back here and read the "Important Stuff" section the first line that was written is about GTX 1660 cards not being able to render and unfortunately my card is a GTX 1660 Super so I guess i was unlucky.
When will you fix this ?
It's been fixed for a long time on the Patreon, the GUI on Itch is just way, WAY out of date.
What is their Patreon ?
https://www.patreon.com/DAINAPP
can someone explain how to actually paint/mark areas with inpaint? i choose a input and i choose inpaint model, what am i missing after that? all it does is render a new image.
for when amd?
whenever i try to load a .ckpt model i get this error message
Traceback (most recent call last):
File "start.py", line 1388, in OnRender
File "start.py", line 1270, in LoadModel
File "convert_original_stable_diffusion_to_diffusers.py", line 630, in Convert
File "omegaconf\omegaconf.py", line 187, in load
FileNotFoundError: [Errno 2] No such file or directory: 'D:\\Downloads\\Stable Diffusion GRisk GUI\\v1-inference.yaml'
I keep getting out of memory errors even when it's only trying to alloc like 9MB. Makes no sense. No solutions online
I ran into an issue where I can run a prompt at 100, 200, 400 and 500 iterations, but 300 iterations gives an error:
Rendering: anime screenshot wide-shot landscape with house in the apple garden, beautiful ambiance, golden hour
0it [00:00, ?it/s]
Traceback (most recent call last):
File "start.py", line 363, in OnRender
File "torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "diffusers\pipelines\stable_diffusion\pipeline_stable_diffusion.py", line 152, in __call__
File "diffusers\schedulers\scheduling_pndm.py", line 136, in step
File "diffusers\schedulers\scheduling_pndm.py", line 212, in step_plms
File "diffusers\schedulers\scheduling_pndm.py", line 230, in _get_prev_sample
IndexError: index 1000 is out of bounds for dimension 0 with size 1000
V Scale is 7.50, resolution is 768x512, seed: 12345, on a 3080 12GB.
Why steps are limited to 500 (even on patreon 0.52 version (also not sure if it's connected in any way but DiscoDiffusion doesn't have a limit))
Processes three random images every time alongside my query. Pretty sus.
are you sure you don't have any backspace in you text followed by nothing? Cause that creates random pics
Every time this has ever happened to me, it meant I had blank lines in the prompt, either before, or after what I actually typed.