Merge branch 'comfyanonymous:master' into master

.github/workflows/stable-release.yml

@@ -112,10 +112,9 @@ jobs:
           ls
 
       - name: Upload binaries to release
-        uses: svenstaro/upload-release-action@v2
+        uses: softprops/action-gh-release@v2
         with:
-          repo_token: ${{ secrets.GITHUB_TOKEN }}
-          file: ComfyUI_windows_portable_${{ inputs.rel_name }}.7z
-          tag: ${{ inputs.git_tag }}
-          overwrite: true
+          files: ComfyUI_windows_portable_${{ inputs.rel_name }}.7z
+          tag_name: ${{ inputs.git_tag }}
           draft: true
+          overwrite_files: true

comfy_extras/nodes_hypertile.py

@@ -1,9 +1,11 @@
 #Taken from: https://github.com/tfernd/HyperTile/
 
 import math
+from typing_extensions import override
 from einops import rearrange
 # Use torch rng for consistency across generations
 from torch import randint
+from comfy_api.latest import ComfyExtension, io
 
 def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int:
     min_value = min(min_value, value)
@@ -20,25 +22,31 @@ def random_divisor(value: int, min_value: int, /, max_options: int = 1) -> int:
 
     return ns[idx]
 
-class HyperTile:
+class HyperTile(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "model": ("MODEL",),
-                             "tile_size": ("INT", {"default": 256, "min": 1, "max": 2048}),
-                             "swap_size": ("INT", {"default": 2, "min": 1, "max": 128}),
-                             "max_depth": ("INT", {"default": 0, "min": 0, "max": 10}),
-                             "scale_depth": ("BOOLEAN", {"default": False}),
-                              }}
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="HyperTile",
+            category="model_patches/unet",
+            inputs=[
+                io.Model.Input("model"),
+                io.Int.Input("tile_size", default=256, min=1, max=2048),
+                io.Int.Input("swap_size", default=2, min=1, max=128),
+                io.Int.Input("max_depth", default=0, min=0, max=10),
+                io.Boolean.Input("scale_depth", default=False),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
 
-    CATEGORY = "model_patches/unet"
-
-    def patch(self, model, tile_size, swap_size, max_depth, scale_depth):
+    @classmethod
+    def execute(cls, model, tile_size, swap_size, max_depth, scale_depth) -> io.NodeOutput:
         latent_tile_size = max(32, tile_size) // 8
-        self.temp = None
+        temp = None
 
         def hypertile_in(q, k, v, extra_options):
+            nonlocal temp
             model_chans = q.shape[-2]
             orig_shape = extra_options['original_shape']
             apply_to = []
@@ -58,14 +66,15 @@ class HyperTile:
 
                 if nh * nw > 1:
                     q = rearrange(q, "b (nh h nw w) c -> (b nh nw) (h w) c", h=h // nh, w=w // nw, nh=nh, nw=nw)
-                    self.temp = (nh, nw, h, w)
+                    temp = (nh, nw, h, w)
                 return q, k, v
 
             return q, k, v
         def hypertile_out(out, extra_options):
-            if self.temp is not None:
-                nh, nw, h, w = self.temp
-                self.temp = None
+            nonlocal temp
+            if temp is not None:
+                nh, nw, h, w = temp
+                temp = None
                 out = rearrange(out, "(b nh nw) hw c -> b nh nw hw c", nh=nh, nw=nw)
                 out = rearrange(out, "b nh nw (h w) c -> b (nh h nw w) c", h=h // nh, w=w // nw)
             return out
@@ -76,6 +85,14 @@ class HyperTile:
         m.set_model_attn1_output_patch(hypertile_out)
         return (m, )
 
-NODE_CLASS_MAPPINGS = {
-    "HyperTile": HyperTile,
-}
+
+class HyperTileExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            HyperTile,
+        ]
+
+
+async def comfy_entrypoint() -> HyperTileExtension:
+    return HyperTileExtension()

comfy_extras/nodes_lotus.py

@@ -1,20 +1,22 @@
+from typing_extensions import override
+
 import torch
 import comfy.model_management as mm
+from comfy_api.latest import ComfyExtension, io
 
-class LotusConditioning:
+
+class LotusConditioning(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {
-            "required": {
-            },
-        }
+    def define_schema(cls):
+        return io.Schema(
+            node_id="LotusConditioning",
+            category="conditioning/lotus",
+            inputs=[],
+            outputs=[io.Conditioning.Output(display_name="conditioning")],
+        )
 
-    RETURN_TYPES = ("CONDITIONING",)
-    RETURN_NAMES = ("conditioning",)
-    FUNCTION = "conditioning"
-    CATEGORY = "conditioning/lotus"
-
-    def conditioning(self):
+    @classmethod
+    def execute(cls) -> io.NodeOutput:
         device = mm.get_torch_device()
         #lotus uses a frozen encoder and null conditioning, i'm just inlining the results of that operation since it doesn't change
         #and getting parity with the reference implementation would otherwise require inference and 800mb of tensors
@@ -22,8 +24,16 @@ class LotusConditioning:
 
         cond = [[prompt_embeds, {}]]
 
-        return (cond,)
+        return io.NodeOutput(cond)
 
-NODE_CLASS_MAPPINGS = {
-    "LotusConditioning" : LotusConditioning,
-}
+
+class LotusExtension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            LotusConditioning,
+        ]
+
+
+async def comfy_entrypoint() -> LotusExtension:
+    return LotusExtension()

comfy_extras/nodes_lumina2.py

@@ -1,20 +1,27 @@
-from comfy.comfy_types import IO, ComfyNodeABC, InputTypeDict
+from typing_extensions import override
 import torch
 
+from comfy_api.latest import ComfyExtension, io
 
-class RenormCFG:
+
+class RenormCFG(io.ComfyNode):
     @classmethod
-    def INPUT_TYPES(s):
-        return {"required": { "model": ("MODEL",),
-                              "cfg_trunc": ("FLOAT", {"default": 100, "min": 0.0, "max": 100.0, "step": 0.01}),
-                              "renorm_cfg": ("FLOAT", {"default": 1.0, "min": 0.0, "max": 100.0, "step": 0.01}),
-                              }}
-    RETURN_TYPES = ("MODEL",)
-    FUNCTION = "patch"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="RenormCFG",
+            category="advanced/model",
+            inputs=[
+                io.Model.Input("model"),
+                io.Float.Input("cfg_trunc", default=100, min=0.0, max=100.0, step=0.01),
+                io.Float.Input("renorm_cfg", default=1.0, min=0.0, max=100.0, step=0.01),
+            ],
+            outputs=[
+                io.Model.Output(),
+            ],
+        )
 
-    CATEGORY = "advanced/model"
-
-    def patch(self, model, cfg_trunc, renorm_cfg):
+    @classmethod
+    def execute(cls, model, cfg_trunc, renorm_cfg) -> io.NodeOutput:
         def renorm_cfg_func(args):
             cond_denoised = args["cond_denoised"]
             uncond_denoised = args["uncond_denoised"]
@@ -53,10 +60,10 @@ class RenormCFG:
 
         m = model.clone()
         m.set_model_sampler_cfg_function(renorm_cfg_func)
-        return (m, )
+        return io.NodeOutput(m)
 
 
-class CLIPTextEncodeLumina2(ComfyNodeABC):
+class CLIPTextEncodeLumina2(io.ComfyNode):
     SYSTEM_PROMPT = {
         "superior": "You are an assistant designed to generate superior images with the superior "\
             "degree of image-text alignment based on textual prompts or user prompts.",
@@ -69,36 +76,52 @@ class CLIPTextEncodeLumina2(ComfyNodeABC):
         "Alignment: You are an assistant designed to generate high-quality images with the highest "\
         "degree of image-text alignment based on textual prompts."
     @classmethod
-    def INPUT_TYPES(s) -> InputTypeDict:
-        return {
-            "required": {
-                "system_prompt": (list(CLIPTextEncodeLumina2.SYSTEM_PROMPT.keys()), {"tooltip": CLIPTextEncodeLumina2.SYSTEM_PROMPT_TIP}),
-                "user_prompt": (IO.STRING, {"multiline": True, "dynamicPrompts": True, "tooltip": "The text to be encoded."}),
-                "clip": (IO.CLIP, {"tooltip": "The CLIP model used for encoding the text."})
-            }
-        }
-    RETURN_TYPES = (IO.CONDITIONING,)
-    OUTPUT_TOOLTIPS = ("A conditioning containing the embedded text used to guide the diffusion model.",)
-    FUNCTION = "encode"
+    def define_schema(cls):
+        return io.Schema(
+            node_id="CLIPTextEncodeLumina2",
+            display_name="CLIP Text Encode for Lumina2",
+            category="conditioning",
+            description="Encodes a system prompt and a user prompt using a CLIP model into an embedding "
+                        "that can be used to guide the diffusion model towards generating specific images.",
+            inputs=[
+                io.Combo.Input(
+                    "system_prompt",
+                    options=list(cls.SYSTEM_PROMPT.keys()),
+                    tooltip=cls.SYSTEM_PROMPT_TIP,
+                ),
+                io.String.Input(
+                    "user_prompt",
+                    multiline=True,
+                    dynamic_prompts=True,
+                    tooltip="The text to be encoded.",
+                ),
+                io.Clip.Input("clip", tooltip="The CLIP model used for encoding the text."),
+            ],
+            outputs=[
+                io.Conditioning.Output(
+                    tooltip="A conditioning containing the embedded text used to guide the diffusion model.",
+                ),
+            ],
+        )
 
-    CATEGORY = "conditioning"
-    DESCRIPTION = "Encodes a system prompt and a user prompt using a CLIP model into an embedding that can be used to guide the diffusion model towards generating specific images."
-
-    def encode(self, clip, user_prompt, system_prompt):
+    @classmethod
+    def execute(cls, clip, user_prompt, system_prompt) -> io.NodeOutput:
         if clip is None:
             raise RuntimeError("ERROR: clip input is invalid: None\n\nIf the clip is from a checkpoint loader node your checkpoint does not contain a valid clip or text encoder model.")
-        system_prompt = CLIPTextEncodeLumina2.SYSTEM_PROMPT[system_prompt]
+        system_prompt = cls.SYSTEM_PROMPT[system_prompt]
         prompt = f'{system_prompt} <Prompt Start> {user_prompt}'
         tokens = clip.tokenize(prompt)
-        return (clip.encode_from_tokens_scheduled(tokens), )
+        return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens))
 
 
-NODE_CLASS_MAPPINGS = {
-    "CLIPTextEncodeLumina2": CLIPTextEncodeLumina2,
-    "RenormCFG": RenormCFG
-}
+class Lumina2Extension(ComfyExtension):
+    @override
+    async def get_node_list(self) -> list[type[io.ComfyNode]]:
+        return [
+            CLIPTextEncodeLumina2,
+            RenormCFG,
+        ]
 
 
-NODE_DISPLAY_NAME_MAPPINGS = {
-    "CLIPTextEncodeLumina2": "CLIP Text Encode for Lumina2",
-}
+async def comfy_entrypoint() -> Lumina2Extension:
+    return Lumina2Extension()

main.py

@@ -127,6 +127,7 @@ if __name__ == "__main__":
     if args.cuda_device is not None:
         os.environ['CUDA_VISIBLE_DEVICES'] = str(args.cuda_device)
         os.environ['HIP_VISIBLE_DEVICES'] = str(args.cuda_device)
+        os.environ["ASCEND_RT_VISIBLE_DEVICES"] = str(args.cuda_device)
         logging.info("Set cuda device to: {}".format(args.cuda_device))
 
     if args.oneapi_device_selector is not None: