Merge branch 'master' into dev/deepdanbooru

4 files changed, 17 insertions, 4 deletions

diff --git a/modules/prompt_parser.py b/modules/prompt_parser.py
index 15666073..919d5d31 100644
--- a/modules/prompt_parser.py
+++ b/modules/prompt_parser.py
@@ -13,13 +13,14 @@ import lark
 

 schedule_parser = lark.Lark(r"""

 !start: (prompt | /[][():]/+)*

-prompt: (emphasized | scheduled | plain | WHITESPACE)*

+prompt: (emphasized | scheduled | alternate | plain | WHITESPACE)*

 !emphasized: "(" prompt ")"

         | "(" prompt ":" prompt ")"

         | "[" prompt "]"

 scheduled: "[" [prompt ":"] prompt ":" [WHITESPACE] NUMBER "]"

+alternate: "[" prompt ("|" prompt)+ "]"

 WHITESPACE: /\s+/

-plain: /([^\\\[\]():]|\\.)+/

+plain: /([^\\\[\]():|]|\\.)+/

 %import common.SIGNED_NUMBER -> NUMBER

 """)

 

@@ -59,6 +60,8 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
                     tree.children[-1] *= steps

                 tree.children[-1] = min(steps, int(tree.children[-1]))

                 l.append(tree.children[-1])

+            def alternate(self, tree):

+                l.extend(range(1, steps+1))

         CollectSteps().visit(tree)

         return sorted(set(l))

 

@@ -67,6 +70,8 @@ def get_learned_conditioning_prompt_schedules(prompts, steps):
             def scheduled(self, args):

                 before, after, _, when = args

                 yield before or () if step <= when else after

+            def alternate(self, args):

+                yield next(args[(step - 1)%len(args)])

             def start(self, args):

                 def flatten(x):

                     if type(x) == str:

diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py
index ed271976..307cc67d 100644
--- a/modules/sd_hijack.py
+++ b/modules/sd_hijack.py
@@ -22,12 +22,16 @@ def apply_optimizations():
     undo_optimizations()

 

     ldm.modules.diffusionmodules.model.nonlinearity = silu

-    if cmd_opts.xformers and shared.xformers_available and not torch.version.hip:

+

+    if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and torch.cuda.get_device_capability(shared.device) == (8, 6)):

+        print("Applying xformers cross attention optimization.")

         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward

         ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward

     elif cmd_opts.opt_split_attention_v1:

+        print("Applying v1 cross attention optimization.")

         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward_v1

     elif not cmd_opts.disable_opt_split_attention and (cmd_opts.opt_split_attention or torch.cuda.is_available()):

+        print("Applying cross attention optimization.")

         ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.split_cross_attention_forward

         ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.cross_attention_attnblock_forward

 

diff --git a/modules/sd_hijack_optimizations.py b/modules/sd_hijack_optimizations.py
index d23d733b..dba21192 100644
--- a/modules/sd_hijack_optimizations.py
+++ b/modules/sd_hijack_optimizations.py
@@ -211,6 +211,7 @@ def cross_attention_attnblock_forward(self, x):
         return h3

     

 def xformers_attnblock_forward(self, x):

+    try:

         h_ = x

         h_ = self.norm(h_)

         q1 = self.q(h_).contiguous()

@@ -218,4 +219,6 @@ def xformers_attnblock_forward(self, x):
         v = self.v(h_).contiguous()

         out = xformers.ops.memory_efficient_attention(q1, k1, v)

         out = self.proj_out(out)

-        return x+out

+        return x + out

+    except NotImplementedError:

+        return cross_attention_attnblock_forward(self, x)

diff --git a/modules/shared.py b/modules/shared.py
index c87b726e..026dce47 100644
--- a/modules/shared.py
+++ b/modules/shared.py
@@ -44,6 +44,7 @@ parser.add_argument("--scunet-models-path", type=str, help="Path to directory wi
 parser.add_argument("--swinir-models-path", type=str, help="Path to directory with SwinIR model file(s).", default=os.path.join(models_path, 'SwinIR'))

 parser.add_argument("--ldsr-models-path", type=str, help="Path to directory with LDSR model file(s).", default=os.path.join(models_path, 'LDSR'))

 parser.add_argument("--xformers", action='store_true', help="enable xformers for cross attention layers")

+parser.add_argument("--force-enable-xformers", action='store_true', help="enable xformers for cross attention layers regardless of whether the checking code thinks you can run it; do not make bug reports if this fails to work")

 parser.add_argument("--deepdanbooru", action='store_true', help="enable deepdanbooru interrogator")

 parser.add_argument("--opt-split-attention", action='store_true', help="force-enables cross-attention layer optimization. By default, it's on for torch.cuda and off for other torch devices.")

 parser.add_argument("--disable-opt-split-attention", action='store_true', help="force-disables cross-attention layer optimization")