mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-09-11 03:58:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Support loading long clipl model with the CLIP loader node.

Browse Source
This commit is contained in:
comfyanonymous
2024-08-20 10:42:40 -04:00
parent 83dbac28eb
commit d1a6bd6845
5 changed files with 55 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
comfy/text_encoders/long_clipl.json Normal file
View File

@@ -0,0 +1,25 @@
{
"_name_or_path": "openai/clip-vit-large-patch14",
"architectures": [
"CLIPTextModel"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"dropout": 0.0,
"eos_token_id": 49407,
"hidden_act": "quick_gelu",
"hidden_size": 768,
"initializer_factor": 1.0,
"initializer_range": 0.02,
"intermediate_size": 3072,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 248,
"model_type": "clip_text_model",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"projection_dim": 768,
"torch_dtype": "float32",
"transformers_version": "4.24.0",
"vocab_size": 49408
}

19
comfy/text_encoders/long_clipl.py Normal file
View File

@@ -0,0 +1,19 @@
from comfy import sd1_clip
import os
class LongClipTokenizer_(sd1_clip.SDTokenizer):
def __init__(self, embedding_directory=None, tokenizer_data={}):
super().__init__(max_length=248, embedding_directory=embedding_directory, tokenizer_data=tokenizer_data)
class LongClipModel_(sd1_clip.SDClipModel):
def __init__(self, device="cpu", dtype=None, model_options={}):
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "long_clipl.json")
super().__init__(device=device, textmodel_json_config=textmodel_json_config, return_projected_pooled=False, dtype=dtype, model_options=model_options)
class LongClipTokenizer(sd1_clip.SD1Tokenizer):
def __init__(self, embedding_directory=None, tokenizer_data={}):
super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, tokenizer=LongClipTokenizer_)
class LongClipModel(sd1_clip.SD1ClipModel):
def __init__(self, device="cpu", dtype=None, model_options={}, **kwargs):
super().__init__(device=device, dtype=dtype, model_options=model_options, clip_model=LongClipModel_, **kwargs)

2
comfy/text_encoders/sd3_clip.py
View File

@@ -15,7 +15,7 @@ class T5XXLModel(sd1_clip.SDClipModel):
class T5XXLTokenizer(sd1_clip.SDTokenizer):
def __init__(self, embedding_directory=None, tokenizer_data={}):
tokenizer_path = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_tokenizer")
super().__init__(tokenizer_path, pad_with_end=False, embedding_size=4096, embedding_key='t5xxl', tokenizer_class=T5TokenizerFast, has_start_token=False, pad_to_max_length=False, max_length=99999999, min_length=77)
super().__init__(tokenizer_path, embedding_directory=embedding_directory, pad_with_end=False, embedding_size=4096, embedding_key='t5xxl', tokenizer_class=T5TokenizerFast, has_start_token=False, pad_to_max_length=False, max_length=99999999, min_length=77)
class SD3Tokenizer: