Add support for unCLIP SD2.x models.

See _for_testing/unclip in the UI for the new nodes.

unCLIPCheckpointLoader is used to load them.

unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.

comfy_extras/clip_vision.py

@@ -1,32 +0,0 @@
-from transformers import CLIPVisionModel, CLIPVisionConfig, CLIPImageProcessor
-from comfy.sd import load_torch_file
-import os
-
-class ClipVisionModel():
-    def __init__(self):
-        json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "clip_vision_config.json")
-        config = CLIPVisionConfig.from_json_file(json_config)
-        self.model = CLIPVisionModel(config)
-        self.processor = CLIPImageProcessor(crop_size=224,
-                                            do_center_crop=True,
-                                            do_convert_rgb=True,
-                                            do_normalize=True,
-                                            do_resize=True,
-                                            image_mean=[ 0.48145466,0.4578275,0.40821073],
-                                            image_std=[0.26862954,0.26130258,0.27577711],
-                                            resample=3, #bicubic
-                                            size=224)
-
-    def load_sd(self, sd):
-        self.model.load_state_dict(sd, strict=False)
-
-    def encode_image(self, image):
-        inputs = self.processor(images=[image[0]], return_tensors="pt")
-        outputs = self.model(**inputs)
-        return outputs
-
-def load(ckpt_path):
-    clip_data = load_torch_file(ckpt_path)
-    clip = ClipVisionModel()
-    clip.load_sd(clip_data)
-    return clip

comfy_extras/clip_vision_config.json

@@ -1,23 +0,0 @@
-{
-  "_name_or_path": "openai/clip-vit-large-patch14",
-  "architectures": [
-    "CLIPVisionModel"
-  ],
-  "attention_dropout": 0.0,
-  "dropout": 0.0,
-  "hidden_act": "quick_gelu",
-  "hidden_size": 1024,
-  "image_size": 224,
-  "initializer_factor": 1.0,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "model_type": "clip_vision_model",
-  "num_attention_heads": 16,
-  "num_channels": 3,
-  "num_hidden_layers": 24,
-  "patch_size": 14,
-  "projection_dim": 768,
-  "torch_dtype": "float32",
-  "transformers_version": "4.24.0"
-}

comfy_extras/nodes_upscale_model.py

@@ -1,6 +1,5 @@
 import os
 from comfy_extras.chainner_models import model_loading
-from comfy.sd import load_torch_file
 import model_management
 import torch
 import comfy.utils
@@ -18,7 +17,7 @@ class UpscaleModelLoader:
 
     def load_model(self, model_name):
         model_path = folder_paths.get_full_path("upscale_models", model_name)
-        sd = load_torch_file(model_path)
+        sd = comfy.utils.load_torch_file(model_path)
         out = model_loading.load_state_dict(sd).eval()
         return (out, )