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.

Add text encode nodes to control the extra parameters in SDXL.

comfyanonymousd94ddd8548f9
diff --git a/comfy_extras/nodes_clip_sdxl.py b/comfy_extras/nodes_clip_sdxl.py
new file mode 100644
index 000000000..9ee23c752
--- /dev/null
+++ b/comfy_extras/nodes_clip_sdxl.py
@@ -0,0 +1,50 @@
+import torch
+from nodes import MAX_RESOLUTION
+
+class CLIPTextEncodeSDXLRefiner:
+ @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}), "clip": ("CLIP", ),
+ }}
+ RETURN_TYPES = ("CONDITIONING",)
+ FUNCTION = "encode"
+
+ CATEGORY = "advanced/conditioning"
+
+ def encode(self, clip, ascore, width, height, text):
+ tokens = clip.tokenize(text)
+ cond, pooled = clip.encode_from_tokens(tokens, return_pooled=True)
+ return ([[cond, {"pooled_output": pooled, "aesthetic_score": ascore, "width": width,"height": height}]], )
+
+class CLIPTextEncodeSDXL:
+ @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}),
+ "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, "default": "CLIP_G"}), "clip": ("CLIP", ),
+ "text_l": ("STRING", {"multiline": True, "default": "CLIP_L"}), "clip": ("CLIP", ),
+ }}
+ 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):
+ tokens = clip.tokenize(text_g)
+ tokens["l"] = clip.tokenize(text_l)["l"]
+ cond, pooled = clip.encode_from_tokens(tokens, return_pooled=True)
+ return ([[cond, {"pooled_output": pooled, "width": width, "height": height, "crop_w": crop_w, "crop_h": crop_h, "target_width": target_width, "target_height": target_height}]], )
+
+NODE_CLASS_MAPPINGS = {
+ "CLIPTextEncodeSDXLRefiner": CLIPTextEncodeSDXLRefiner,
+ "CLIPTextEncodeSDXL": CLIPTextEncodeSDXL,
+}
diff --git a/nodes.py b/nodes.py
index a9f2e962e..d9c269462 100644
--- a/nodes.py
+++ b/nodes.py
@@ -1501,4 +1501,5 @@ def init_custom_nodes():
load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_rebatch.py"))
load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_model_merging.py"))
load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_tomesd.py"))
+ load_custom_node(os.path.join(os.path.join(os.path.dirname(os.path.realpath(__file__)), "comfy_extras"), "nodes_clip_sdxl.py"))
load_custom_nodes()