Merge branch 'master' into dev/deepdanbooru

launch.py

@@ -127,7 +127,7 @@ if not is_installed("gfpgan"):
 if not is_installed("clip"):
     run_pip(f"install {clip_package}", "clip")
 
-if not is_installed("xformers") and xformers:
+if not is_installed("xformers") and xformers and platform.python_version().startswith("3.10"):
     if platform.system() == "Windows":
         run_pip("install https://github.com/C43H66N12O12S2/stable-diffusion-webui/releases/download/a/xformers-0.0.14.dev0-cp310-cp310-win_amd64.whl", "xformers")
     elif platform.system() == "Linux":

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:

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
 

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()
@@ -219,3 +220,5 @@ def xformers_attnblock_forward(self, x):
         out = xformers.ops.memory_efficient_attention(q1, k1, v)
         out = self.proj_out(out)
         return x + out
+    except NotImplementedError:
+        return cross_attention_attnblock_forward(self, x)

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")

webui.py

@@ -5,6 +5,8 @@ import importlib
 import signal
 import threading
 
+from fastapi.middleware.gzip import GZipMiddleware
+
 from modules.paths import script_path
 
 from modules import devices, sd_samplers
@@ -93,7 +95,7 @@ def webui():
 
         demo = modules.ui.create_ui(wrap_gradio_gpu_call=wrap_gradio_gpu_call)
         
-        demo.launch(
+        app,local_url,share_url = demo.launch(
             share=cmd_opts.share,
             server_name="0.0.0.0" if cmd_opts.listen else None,
             server_port=cmd_opts.port,
@@ -103,6 +105,8 @@ def webui():
             prevent_thread_lock=True
         )
         
+        app.add_middleware(GZipMiddleware,minimum_size=1000)
+
         while 1:
             time.sleep(0.5)
             if getattr(demo, 'do_restart', False):