Skip to content

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.

convert CLIPTextEncodeSDXL nodes to V3 schema (#9716)

Alexander Piskuncd66d72b464f
diff --git a/comfy_extras/nodes_clip_sdxl.py b/comfy_extras/nodes_clip_sdxl.py
index 14269caf3..520ff0e3c 100644
--- a/comfy_extras/nodes_clip_sdxl.py
+++ b/comfy_extras/nodes_clip_sdxl.py
@@ -1,43 +1,52 @@
-from nodes import MAX_RESOLUTION
+from typing_extensions import override
-class CLIPTextEncodeSDXLRefiner:
+import nodes
+from comfy_api.latest import ComfyExtension, io
+
+
+class CLIPTextEncodeSDXLRefiner(io.ComfyNode):
@classmethod
- def INPUT_TYPES(s):
- return {"required": {
- "ascore": ("FLOAT", {"default": 6.0, "min": 0.0, "max": 1000.0, "step": 0.01}),
- "width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
- "height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
- "text": ("STRING", {"multiline": True, "dynamicPrompts": True}), "clip": ("CLIP", ),
- }}
- RETURN_TYPES = ("CONDITIONING",)
- FUNCTION = "encode"
-
- CATEGORY = "advanced/conditioning"
-
- def encode(self, clip, ascore, width, height, text):
+ def define_schema(cls):
+ return io.Schema(
+ node_id="CLIPTextEncodeSDXLRefiner",
+ category="advanced/conditioning",
+ inputs=[
+ io.Float.Input("ascore", default=6.0, min=0.0, max=1000.0, step=0.01),
+ io.Int.Input("width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+ io.Int.Input("height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+ io.String.Input("text", multiline=True, dynamic_prompts=True),
+ io.Clip.Input("clip"),
+ ],
+ outputs=[io.Conditioning.Output()],
+ )
+
+ @classmethod
+ def execute(cls, clip, ascore, width, height, text) -> io.NodeOutput:
tokens = clip.tokenize(text)
- return (clip.encode_from_tokens_scheduled(tokens, add_dict={"aesthetic_score": ascore, "width": width, "height": height}), )
+ return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens, add_dict={"aesthetic_score": ascore, "width": width, "height": height}))
-class CLIPTextEncodeSDXL:
+class CLIPTextEncodeSDXL(io.ComfyNode):
@classmethod
- def INPUT_TYPES(s):
- return {"required": {
- "clip": ("CLIP", ),
- "width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
- "height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
- "crop_w": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION}),
- "crop_h": ("INT", {"default": 0, "min": 0, "max": MAX_RESOLUTION}),
- "target_width": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
- "target_height": ("INT", {"default": 1024.0, "min": 0, "max": MAX_RESOLUTION}),
- "text_g": ("STRING", {"multiline": True, "dynamicPrompts": True}),
- "text_l": ("STRING", {"multiline": True, "dynamicPrompts": True}),
- }}
- RETURN_TYPES = ("CONDITIONING",)
- FUNCTION = "encode"
-
- CATEGORY = "advanced/conditioning"
-
- def encode(self, clip, width, height, crop_w, crop_h, target_width, target_height, text_g, text_l):
+ def define_schema(cls):
+ return io.Schema(
+ node_id="CLIPTextEncodeSDXL",
+ category="advanced/conditioning",
+ inputs=[
+ io.Clip.Input("clip"),
+ io.Int.Input("width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+ io.Int.Input("height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+ io.Int.Input("crop_w", default=0, min=0, max=nodes.MAX_RESOLUTION),
+ io.Int.Input("crop_h", default=0, min=0, max=nodes.MAX_RESOLUTION),
+ io.Int.Input("target_width", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+ io.Int.Input("target_height", default=1024, min=0, max=nodes.MAX_RESOLUTION),
+ io.String.Input("text_g", multiline=True, dynamic_prompts=True),
+ io.String.Input("text_l", multiline=True, dynamic_prompts=True),
+ ],
+ outputs=[io.Conditioning.Output()],
+ )
+
+ @classmethod
+ def execute(cls, clip, width, height, crop_w, crop_h, target_width, target_height, text_g, text_l) -> io.NodeOutput:
tokens = clip.tokenize(text_g)
tokens["l"] = clip.tokenize(text_l)["l"]
if len(tokens["l"]) != len(tokens["g"]):
@@ -46,9 +55,17 @@ class CLIPTextEncodeSDXL:
tokens["l"] += empty["l"]
while len(tokens["l"]) > len(tokens["g"]):
tokens["g"] += empty["g"]
- return (clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height, "crop_w": crop_w, "crop_h": crop_h, "target_width": target_width, "target_height": target_height}), )
+ return io.NodeOutput(clip.encode_from_tokens_scheduled(tokens, add_dict={"width": width, "height": height, "crop_w": crop_w, "crop_h": crop_h, "target_width": target_width, "target_height": target_height}))
+
+
+class ClipSdxlExtension(ComfyExtension):
+ @override
+ async def get_node_list(self) -> list[type[io.ComfyNode]]:
+ return [
+ CLIPTextEncodeSDXLRefiner,
+ CLIPTextEncodeSDXL,
+ ]
+
-NODE_CLASS_MAPPINGS = {
- "CLIPTextEncodeSDXLRefiner": CLIPTextEncodeSDXLRefiner,
- "CLIPTextEncodeSDXL": CLIPTextEncodeSDXL,
-}
+async def comfy_entrypoint() -> ClipSdxlExtension:
+ return ClipSdxlExtension()