Merge branch 'master' into cpu-cmdline-opt

1 files changed, 11 insertions, 7 deletions

diff --git a/modules/processing.py b/modules/processing.py
index 0a4b6198..6f5599c7 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -1,4 +1,3 @@
-import contextlib

 import json

 import math

 import os

@@ -330,9 +329,8 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
 

     infotexts = []

     output_images = []

-    precision_scope = torch.autocast if cmd_opts.precision == "autocast" else contextlib.nullcontext

-    ema_scope = (contextlib.nullcontext if cmd_opts.lowvram else p.sd_model.ema_scope)

-    with torch.no_grad(), precision_scope("cuda"), ema_scope():

+

+    with torch.no_grad():

         p.init(all_prompts, all_seeds, all_subseeds)

 

         if state.job_count == -1:

@@ -351,8 +349,9 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
 

             #uc = p.sd_model.get_learned_conditioning(len(prompts) * [p.negative_prompt])

             #c = p.sd_model.get_learned_conditioning(prompts)

-            uc = prompt_parser.get_learned_conditioning(len(prompts) * [p.negative_prompt], p.steps)

-            c = prompt_parser.get_learned_conditioning(prompts, p.steps)

+            with devices.autocast():

+                uc = prompt_parser.get_learned_conditioning(len(prompts) * [p.negative_prompt], p.steps)

+                c = prompt_parser.get_learned_conditioning(prompts, p.steps)

 

             if len(model_hijack.comments) > 0:

                 for comment in model_hijack.comments:

@@ -361,13 +360,17 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
             if p.n_iter > 1:

                 shared.state.job = f"Batch {n+1} out of {p.n_iter}"

 

-            samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength)

+            with devices.autocast():

+                samples_ddim = p.sample(conditioning=c, unconditional_conditioning=uc, seeds=seeds, subseeds=subseeds, subseed_strength=p.subseed_strength)

+

             if state.interrupted:

 

                 # if we are interruped, sample returns just noise

                 # use the image collected previously in sampler loop

                 samples_ddim = shared.state.current_latent

 

+            samples_ddim = samples_ddim.to(devices.dtype)

+

             x_samples_ddim = p.sd_model.decode_first_stage(samples_ddim)

             x_samples_ddim = torch.clamp((x_samples_ddim + 1.0) / 2.0, min=0.0, max=1.0)

 

@@ -386,6 +389,7 @@ def process_images(p: StableDiffusionProcessing) -> Processed:
                     devices.torch_gc()

 

                     x_sample = modules.face_restoration.restore_faces(x_sample)

+                    devices.torch_gc()

 

                 image = Image.fromarray(x_sample)