Lincoln Stein
ddb007af65
Merge branch 'development' into fix-high-step-count
2022-10-21 06:55:17 -04:00
wfng92
1c2bd275fe
Fix img2img DDIM index out of bound
...
Added a [community solution](https://github.com/CompVis/stable-diffusion/issues/111#issuecomment-1229483511 ) to fix index out of bound when doing img2img generation with `ddim` sampler. Also, restored `steps_out` to be `ddim_timesteps + 1` since the removal was meant to fix the [1000 steps issue](https://github.com/CompVis/stable-diffusion/issues/111 )
2022-10-17 22:32:15 -04:00
Arthur Holstvoogd
595d15455a
Fix generation of image with s>1000
2022-10-06 15:49:35 +02:00
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
Lincoln Stein
653144694f
work around unexplained crash when timesteps=1000 ( #440 )
...
* work around unexplained crash when timesteps=1000
* this fix seems to work
2022-09-08 20:41:37 -04:00
Lincoln Stein
4f02b72c9c
prettified all the code using "blue" at the urging of @tildebyte
2022-08-26 03:15:42 -04:00
Sean McLellan
8952196bbf
Add personalization
2022-08-23 18:26:28 -04:00
ablattmann
171cf29fb5
add configs for training unconditional/class-conditional ldms
2021-12-22 15:57:23 +01:00
ablattmann
e66308c7f2
add code
2021-12-21 03:23:41 +01:00
