InvokeAI/ldm
Mihai 071f65a892
Enable even larger images with one simple torch.nn.functional.silu import (#653)
Fixes:
File "stable-diffusion/ldm/modules/diffusionmodules/model.py", line 37, in nonlinearity
    return x*torch.sigmoid(x)
RuntimeError: CUDA out of memory. Tried to allocate 1.56 GiB [..]

Now up to 1536x1280 is possible on 8GB VRAM.
Also remove unused SiLU class.
2022-09-17 18:03:52 -04:00
..
data prettified all the code using "blue" at the urging of @tildebyte 2022-08-26 03:15:42 -04:00
dream minor fix to ldm.dream.args 2022-09-17 13:44:39 -04:00
gfpgan implementation of RFC #266 (#587) 2022-09-16 13:09:04 -04:00
models Refactor generate.py and dream.py (#534) 2022-09-14 07:02:31 -04:00
modules Enable even larger images with one simple torch.nn.functional.silu import (#653) 2022-09-17 18:03:52 -04:00
generate.py Merge with PR #602 2022-09-16 16:35:34 -04:00
lr_scheduler.py prettified all the code using "blue" at the urging of @tildebyte 2022-08-26 03:15:42 -04:00
simplet2i.py Disabled debug output (#436) 2022-09-11 22:34:35 -04:00
util.py prettified all the code using "blue" at the urging of @tildebyte 2022-08-26 03:15:42 -04:00