Make it possible to load tokenizer data from checkpoints.

This commit is contained in:
comfyanonymous
2024-07-24 16:43:53 -04:00
parent ce80e69fb8
commit 10c919f4c7
8 changed files with 26 additions and 31 deletions

View File

@@ -9,13 +9,13 @@ class T5BaseModel(sd1_clip.SDClipModel):
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"end": 1, "pad": 0}, model_class=comfy.text_encoders.t5.T5, enable_attention_masks=True, zero_out_masked=True)
class T5BaseTokenizer(sd1_clip.SDTokenizer):
def __init__(self, embedding_directory=None):
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=768, embedding_key='t5base', tokenizer_class=T5TokenizerFast, has_start_token=False, pad_to_max_length=False, max_length=99999999, min_length=128)
class SAT5Tokenizer(sd1_clip.SD1Tokenizer):
def __init__(self, embedding_directory=None):
super().__init__(embedding_directory=embedding_directory, clip_name="t5base", tokenizer=T5BaseTokenizer)
def __init__(self, embedding_directory=None, tokenizer_data={}):
super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, clip_name="t5base", tokenizer=T5BaseTokenizer)
class SAT5Model(sd1_clip.SD1ClipModel):
def __init__(self, device="cpu", dtype=None, **kwargs):