github/stable-diffusion-webui
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Holy $hit.

Browse Source 
Yep.

Fix gfpgan_model_arch requirement(s).
Add Upscaler base class, move from images.
Add a lot of methods to Upscaler.
Re-work all the child upscalers to be proper classes.
Add BSRGAN scaler.
Add ldsr_model_arch class, removing the dependency for another repo that just uses regular latent-diffusion stuff.
Add one universal method that will always find and load new upscaler models without having to add new "setup_model" calls. Still need to add command line params, but that could probably be automated.
Add a "self.scale" property to all Upscalers so the scalers themselves can do "things" in response to the requested upscaling size.
Ensure LDSR doesn't get stuck in a longer loop of "upscale/downscale/upscale" as we try to reach the target upscale size.
Add typehints for IDE sanity.
PEP-8 improvements.
Moar.
This commit is contained in:
d8ahazard
2022-09-29 17:46:23 -05:00
parent 31ad536c33
commit 0dce0df1ee
18 changed files with 1009 additions and 641 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/sd_samplers.py
+2 -2
View File
@@ -154,9 +154,9 @@ class VanillaStableDiffusionSampler:
# existing code fails with cetin step counts, like 9
try:
samples_ddim, _ = self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=p.ddim_eta)
samples_ddim, _ = self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_t=x, eta=p.ddim_eta)
except Exception:
samples_ddim, _ = self.sampler.sample(S=steps+1, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=p.ddim_eta)
samples_ddim, _ = self.sampler.sample(S=steps+1, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_t=x, eta=p.ddim_eta)
return samples_ddim