Merge branch 'master' of github.com:comfyanonymous/ComfyUI into feat/linux-amd-setup

.github/workflows/check-line-endings.yml

@@ -0,0 +1,40 @@
+name: Check for Windows Line Endings
+
+on:
+  pull_request:
+    branches: ['*'] # Trigger on all pull requests to any branch
+
+jobs:
+  check-line-endings:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0 # Fetch all history to compare changes
+
+      - name: Check for Windows line endings (CRLF)
+        run: |
+          # Get the list of changed files in the PR
+          CHANGED_FILES=$(git diff --name-only origin/${{ github.base_ref }}..HEAD)
+
+          # Flag to track if CRLF is found
+          CRLF_FOUND=false
+
+          # Loop through each changed file
+          for FILE in $CHANGED_FILES; do
+            # Check if the file exists and is a text file
+            if [ -f "$FILE" ] && file "$FILE" | grep -q "text"; then
+              # Check for CRLF line endings
+              if grep -UP '\r$' "$FILE"; then
+                echo "Error: Windows line endings (CRLF) detected in $FILE"
+                CRLF_FOUND=true
+              fi
+            fi
+          done
+
+          # Exit with error if CRLF was found
+          if [ "$CRLF_FOUND" = true ]; then
+            exit 1
+          fi

comfy/cli_args.py

@@ -144,6 +144,7 @@ class PerformanceFeature(enum.Enum):
 parser.add_argument("--fast", nargs="*", type=PerformanceFeature, help="Enable some untested and potentially quality deteriorating optimizations. --fast with no arguments enables everything. You can pass a list specific optimizations if you only want to enable specific ones. Current valid optimizations: fp16_accumulation fp8_matrix_mult cublas_ops")
 
 parser.add_argument("--mmap-torch-files", action="store_true", help="Use mmap when loading ckpt/pt files.")
+parser.add_argument("--disable-mmap", action="store_true", help="Don't use mmap when loading safetensors.")
 
 parser.add_argument("--dont-print-server", action="store_true", help="Don't print server output.")
 parser.add_argument("--quick-test-for-ci", action="store_true", help="Quick test for CI.")

comfy/supported_models.py

@@ -1214,7 +1214,7 @@ class Omnigen2(supported_models_base.BASE):
     def clip_target(self, state_dict={}):
         pref = self.text_encoder_key_prefix[0]
         hunyuan_detect = comfy.text_encoders.hunyuan_video.llama_detect(state_dict, "{}qwen25_3b.transformer.".format(pref))
-        return supported_models_base.ClipTarget(comfy.text_encoders.omnigen2.LuminaTokenizer, comfy.text_encoders.omnigen2.te(**hunyuan_detect))
+        return supported_models_base.ClipTarget(comfy.text_encoders.omnigen2.Omnigen2Tokenizer, comfy.text_encoders.omnigen2.te(**hunyuan_detect))
 
 
 models = [LotusD, Stable_Zero123, SD15_instructpix2pix, SD15, SD20, SD21UnclipL, SD21UnclipH, SDXL_instructpix2pix, SDXLRefiner, SDXL, SSD1B, KOALA_700M, KOALA_1B, Segmind_Vega, SD_X4Upscaler, Stable_Cascade_C, Stable_Cascade_B, SV3D_u, SV3D_p, SD3, StableAudio, AuraFlow, PixArtAlpha, PixArtSigma, HunyuanDiT, HunyuanDiT1, FluxInpaint, Flux, FluxSchnell, GenmoMochi, LTXV, HunyuanVideoSkyreelsI2V, HunyuanVideoI2V, HunyuanVideo, CosmosT2V, CosmosI2V, CosmosT2IPredict2, CosmosI2VPredict2, Lumina2, WAN21_T2V, WAN21_I2V, WAN21_FunControl2V, WAN21_Vace, WAN21_Camera, Hunyuan3Dv2mini, Hunyuan3Dv2, HiDream, Chroma, ACEStep, Omnigen2]

comfy/utils.py

@@ -31,6 +31,7 @@ from einops import rearrange
 from comfy.cli_args import args
 
 MMAP_TORCH_FILES = args.mmap_torch_files
+DISABLE_MMAP = args.disable_mmap
 
 ALWAYS_SAFE_LOAD = False
 if hasattr(torch.serialization, "add_safe_globals"):  # TODO: this was added in pytorch 2.4, the unsafe path should be removed once earlier versions are deprecated
@@ -58,7 +59,10 @@ def load_torch_file(ckpt, safe_load=False, device=None, return_metadata=False):
             with safetensors.safe_open(ckpt, framework="pt", device=device.type) as f:
                 sd = {}
                 for k in f.keys():
-                    sd[k] = f.get_tensor(k)
+                    tensor = f.get_tensor(k)
+                    if DISABLE_MMAP:  # TODO: Not sure if this is the best way to bypass the mmap issues
+                        tensor = tensor.to(device=device, copy=True)
+                    sd[k] = tensor
                 if return_metadata:
                     metadata = f.metadata()
         except Exception as e:

comfy_api_nodes/nodes_gemini.py

@@ -406,7 +406,7 @@ class GeminiInputFiles(ComfyNodeABC):
 
     def create_file_part(self, file_path: str) -> GeminiPart:
         mime_type = (
-            GeminiMimeType.pdf
+            GeminiMimeType.application_pdf
             if file_path.endswith(".pdf")
             else GeminiMimeType.text_plain
         )

comfy_extras/nodes_mask.py

@@ -247,7 +247,7 @@ class MaskComposite:
         visible_width, visible_height = (right - left, bottom - top,)
 
         source_portion = source[:, :visible_height, :visible_width]
-        destination_portion = destination[:, top:bottom, left:right]
+        destination_portion = output[:, top:bottom, left:right]
 
         if operation == "multiply":
             output[:, top:bottom, left:right] = destination_portion * source_portion

comfy_extras/nodes_pixart.py

@@ -1,24 +1,24 @@
-from nodes import MAX_RESOLUTION
-
-class CLIPTextEncodePixArtAlpha:
-    @classmethod
-    def INPUT_TYPES(s):
-        return {"required": {
-            "width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            "height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
-            # "aspect_ratio": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
-            "text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ),
-            }}
-
-    RETURN_TYPES = ("CONDITIONING",)
-    FUNCTION = "encode"
-    CATEGORY = "advanced/conditioning"
-    DESCRIPTION = "Encodes text and sets the resolution conditioning for PixArt Alpha. Does not apply to PixArt Sigma."
-
-    def encode(self, clip, width, height, text):
-        tokens = clip.tokenize(text)
-        return (clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height}),)
-
-NODE_CLASS_MAPPINGS = {
-    "CLIPTextEncodePixArtAlpha": CLIPTextEncodePixArtAlpha,
-}
+from nodes import MAX_RESOLUTION
+
+class CLIPTextEncodePixArtAlpha:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {
+            "width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
+            "height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
+            # "aspect_ratio": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 10.0, "step": 0.01}),
+            "text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ),
+            }}
+
+    RETURN_TYPES = ("CONDITIONING",)
+    FUNCTION = "encode"
+    CATEGORY = "advanced/conditioning"
+    DESCRIPTION = "Encodes text and sets the resolution conditioning for PixArt Alpha. Does not apply to PixArt Sigma."
+
+    def encode(self, clip, width, height, text):
+        tokens = clip.tokenize(text)
+        return (clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height}),)
+
+NODE_CLASS_MAPPINGS = {
+    "CLIPTextEncodePixArtAlpha": CLIPTextEncodePixArtAlpha,
+}

requirements.txt

@@ -1,5 +1,5 @@
 comfyui-frontend-package==1.23.4
-comfyui-workflow-templates==0.1.35
+comfyui-workflow-templates==0.1.36
 comfyui-embedded-docs==0.2.4
 torch
 torchsde

script_examples/websockets_api_example.py

@@ -10,11 +10,11 @@ import urllib.parse
 server_address = "127.0.0.1:8188"
 client_id = str(uuid.uuid4())
 
-def queue_prompt(prompt):
-    p = {"prompt": prompt, "client_id": client_id}
+def queue_prompt(prompt, prompt_id):
+    p = {"prompt": prompt, "client_id": client_id, "prompt_id": prompt_id}
     data = json.dumps(p).encode('utf-8')
-    req =  urllib.request.Request("http://{}/prompt".format(server_address), data=data)
-    return json.loads(urllib.request.urlopen(req).read())
+    req = urllib.request.Request("http://{}/prompt".format(server_address), data=data)
+    urllib.request.urlopen(req).read()
 
 def get_image(filename, subfolder, folder_type):
     data = {"filename": filename, "subfolder": subfolder, "type": folder_type}
@@ -27,7 +27,8 @@ def get_history(prompt_id):
         return json.loads(response.read())
 
 def get_images(ws, prompt):
-    prompt_id = queue_prompt(prompt)['prompt_id']
+    prompt_id = str(uuid.uuid4())
+    queue_prompt(prompt, prompt_id)
     output_images = {}
     while True:
         out = ws.recv()

server.py

@@ -678,7 +678,7 @@ class PromptServer():
 
             if "prompt" in json_data:
                 prompt = json_data["prompt"]
-                prompt_id = str(uuid.uuid4())
+                prompt_id = str(json_data.get("prompt_id", uuid.uuid4()))
                 valid = await execution.validate_prompt(prompt_id, prompt)
                 extra_data = {}
                 if "extra_data" in json_data: