Refactor: Move sd2_clip.py to text_encoders folder.

comfy/text_encoders/sd2_clip.py

@@ -0,0 +1,23 @@
+from comfy import sd1_clip
+import os
+
+class SD2ClipHModel(sd1_clip.SDClipModel):
+    def __init__(self, arch="ViT-H-14", device="cpu", max_length=77, freeze=True, layer="penultimate", layer_idx=None, dtype=None):
+        if layer == "penultimate":
+            layer="hidden"
+            layer_idx=-2
+
+        textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "sd2_clip_config.json")
+        super().__init__(device=device, freeze=freeze, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"start": 49406, "end": 49407, "pad": 0})
+
+class SD2ClipHTokenizer(sd1_clip.SDTokenizer):
+    def __init__(self, tokenizer_path=None, embedding_directory=None, tokenizer_data={}):
+        super().__init__(tokenizer_path, pad_with_end=False, embedding_directory=embedding_directory, embedding_size=1024)
+
+class SD2Tokenizer(sd1_clip.SD1Tokenizer):
+    def __init__(self, embedding_directory=None, tokenizer_data={}):
+        super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, clip_name="h", tokenizer=SD2ClipHTokenizer)
+
+class SD2ClipModel(sd1_clip.SD1ClipModel):
+    def __init__(self, device="cpu", dtype=None, **kwargs):
+        super().__init__(device=device, dtype=dtype, clip_name="h", clip_model=SD2ClipHModel, **kwargs)

comfy/text_encoders/sd2_clip_config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "projection_dim": 1024,
+  "torch_dtype": "float32",
+  "vocab_size": 49408
+}