netadmin/test
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

sync with repo 28.08

Browse Source
This commit is contained in:
netadmin
2024-08-28 19:33:34 +03:00
parent 727693318c
commit ad1e3ecbcb
134 changed files with 112534 additions and 12635 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
comfy/text_encoders/aura_t5.py
View File

@@ -4,9 +4,9 @@ import comfy.text_encoders.t5
import os
class PT5XlModel(sd1_clip.SDClipModel):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None, model_options={}):
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_pile_config_xl.json")
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"end": 2, "pad": 1}, model_class=comfy.text_encoders.t5.T5, enable_attention_masks=True, zero_out_masked=True)
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"end": 2, "pad": 1}, model_class=comfy.text_encoders.t5.T5, enable_attention_masks=True, zero_out_masked=True, model_options=model_options)
class PT5XlTokenizer(sd1_clip.SDTokenizer):
def __init__(self, embedding_directory=None, tokenizer_data={}):
@@ -18,5 +18,5 @@ class AuraT5Tokenizer(sd1_clip.SD1Tokenizer):
super().__init__(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, clip_name="pile_t5xl", tokenizer=PT5XlTokenizer)
class AuraT5Model(sd1_clip.SD1ClipModel):
def __init__(self, device="cpu", dtype=None, **kwargs):
super().__init__(device=device, dtype=dtype, name="pile_t5xl", clip_model=PT5XlModel, **kwargs)
def __init__(self, device="cpu", dtype=None, model_options={}, **kwargs):
super().__init__(device=device, dtype=dtype, model_options=model_options, name="pile_t5xl", clip_model=PT5XlModel, **kwargs)

18
comfy/text_encoders/flux.py
View File

@@ -6,9 +6,9 @@ import torch
import os
class T5XXLModel(sd1_clip.SDClipModel):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None, model_options={}):
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_config_xxl.json")
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)
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, model_options=model_options)
class T5XXLTokenizer(sd1_clip.SDTokenizer):
def __init__(self, embedding_directory=None, tokenizer_data={}):
@@ -35,11 +35,11 @@ class FluxTokenizer:
class FluxClipModel(torch.nn.Module):
def __init__(self, dtype_t5=None, device="cpu", dtype=None):
def __init__(self, dtype_t5=None, device="cpu", dtype=None, model_options={}):
super().__init__()
dtype_t5 = comfy.model_management.pick_weight_dtype(dtype_t5, dtype, device)
self.clip_l = sd1_clip.SDClipModel(device=device, dtype=dtype, return_projected_pooled=False)
self.t5xxl = T5XXLModel(device=device, dtype=dtype_t5)
self.clip_l = sd1_clip.SDClipModel(device=device, dtype=dtype, return_projected_pooled=False, model_options=model_options)
self.t5xxl = T5XXLModel(device=device, dtype=dtype_t5, model_options=model_options)
self.dtypes = set([dtype, dtype_t5])
def set_clip_options(self, options):
@@ -52,9 +52,9 @@ class FluxClipModel(torch.nn.Module):
def encode_token_weights(self, token_weight_pairs):
token_weight_pairs_l = token_weight_pairs["l"]
token_weight_pars_t5 = token_weight_pairs["t5xxl"]
token_weight_pairs_t5 = token_weight_pairs["t5xxl"]
t5_out, t5_pooled = self.t5xxl.encode_token_weights(token_weight_pars_t5)
t5_out, t5_pooled = self.t5xxl.encode_token_weights(token_weight_pairs_t5)
l_out, l_pooled = self.clip_l.encode_token_weights(token_weight_pairs_l)
return t5_out, l_pooled
@@ -66,6 +66,6 @@ class FluxClipModel(torch.nn.Module):
def flux_clip(dtype_t5=None):
class FluxClipModel_(FluxClipModel):
def __init__(self, device="cpu", dtype=None):
super().__init__(dtype_t5=dtype_t5, device=device, dtype=dtype)
def __init__(self, device="cpu", dtype=None, model_options={}):
super().__init__(dtype_t5=dtype_t5, device=device, dtype=dtype, model_options=model_options)
return FluxClipModel_

14
comfy/text_encoders/hydit.py
View File

@@ -7,9 +7,9 @@ import os
import torch
class HyditBertModel(sd1_clip.SDClipModel):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None, model_options={}):
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "hydit_clip.json")
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"start": 101, "end": 102, "pad": 0}, model_class=BertModel, enable_attention_masks=True, return_attention_masks=True)
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, special_tokens={"start": 101, "end": 102, "pad": 0}, model_class=BertModel, enable_attention_masks=True, return_attention_masks=True, model_options=model_options)
class HyditBertTokenizer(sd1_clip.SDTokenizer):
def __init__(self, embedding_directory=None, tokenizer_data={}):
@@ -18,9 +18,9 @@ class HyditBertTokenizer(sd1_clip.SDTokenizer):
class MT5XLModel(sd1_clip.SDClipModel):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None, model_options={}):
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "mt5_config_xl.json")
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, return_attention_masks=True)
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, return_attention_masks=True, model_options=model_options)
class MT5XLTokenizer(sd1_clip.SDTokenizer):
def __init__(self, embedding_directory=None, tokenizer_data={}):
@@ -50,10 +50,10 @@ class HyditTokenizer:
return {"mt5xl.spiece_model": self.mt5xl.state_dict()["spiece_model"]}
class HyditModel(torch.nn.Module):
def __init__(self, device="cpu", dtype=None):
def __init__(self, device="cpu", dtype=None, model_options={}):
super().__init__()
self.hydit_clip = HyditBertModel(dtype=dtype)
self.mt5xl = MT5XLModel(dtype=dtype)
self.hydit_clip = HyditBertModel(dtype=dtype, model_options=model_options)
self.mt5xl = MT5XLModel(dtype=dtype, model_options=model_options)
self.dtypes = set()
if dtype is not None:

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)

8
comfy/text_encoders/sa_t5.py
View File

@@ -4,9 +4,9 @@ import comfy.text_encoders.t5
import os
class T5BaseModel(sd1_clip.SDClipModel):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None, model_options={}):
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_config_base.json")
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)
super().__init__(device=device, layer=layer, layer_idx=layer_idx, textmodel_json_config=textmodel_json_config, dtype=dtype, model_options=model_options, 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, tokenizer_data={}):
@@ -18,5 +18,5 @@ class SAT5Tokenizer(sd1_clip.SD1Tokenizer):
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):
super().__init__(device=device, dtype=dtype, name="t5base", clip_model=T5BaseModel, **kwargs)
def __init__(self, device="cpu", dtype=None, model_options={}, **kwargs):
super().__init__(device=device, dtype=dtype, model_options=model_options, name="t5base", clip_model=T5BaseModel, **kwargs)

8
comfy/text_encoders/sd2_clip.py
View File

@@ -2,13 +2,13 @@ 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):
def __init__(self, arch="ViT-H-14", device="cpu", max_length=77, freeze=True, layer="penultimate", layer_idx=None, dtype=None, model_options={}):
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})
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}, return_projected_pooled=True, model_options=model_options)
class SD2ClipHTokenizer(sd1_clip.SDTokenizer):
def __init__(self, tokenizer_path=None, embedding_directory=None, tokenizer_data={}):
@@ -19,5 +19,5 @@ class SD2Tokenizer(sd1_clip.SD1Tokenizer):
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)
def __init__(self, device="cpu", dtype=None, model_options={}, **kwargs):
super().__init__(device=device, dtype=dtype, model_options=model_options, clip_name="h", clip_model=SD2ClipHModel, **kwargs)

22
comfy/text_encoders/sd3_clip.py
View File

@@ -8,14 +8,14 @@ import comfy.model_management
import logging
class T5XXLModel(sd1_clip.SDClipModel):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None):
def __init__(self, device="cpu", layer="last", layer_idx=None, dtype=None, model_options={}):
textmodel_json_config = os.path.join(os.path.dirname(os.path.realpath(__file__)), "t5_config_xxl.json")
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)
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, model_options=model_options)
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:
@@ -38,24 +38,24 @@ class SD3Tokenizer:
return {}
class SD3ClipModel(torch.nn.Module):
def __init__(self, clip_l=True, clip_g=True, t5=True, dtype_t5=None, device="cpu", dtype=None):
def __init__(self, clip_l=True, clip_g=True, t5=True, dtype_t5=None, device="cpu", dtype=None, model_options={}):
super().__init__()
self.dtypes = set()
if clip_l:
self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=-2, device=device, dtype=dtype, layer_norm_hidden_state=False, return_projected_pooled=False)
self.clip_l = sd1_clip.SDClipModel(layer="hidden", layer_idx=-2, device=device, dtype=dtype, layer_norm_hidden_state=False, return_projected_pooled=False, model_options=model_options)
self.dtypes.add(dtype)
else:
self.clip_l = None
if clip_g:
self.clip_g = sdxl_clip.SDXLClipG(device=device, dtype=dtype)
self.clip_g = sdxl_clip.SDXLClipG(device=device, dtype=dtype, model_options=model_options)
self.dtypes.add(dtype)
else:
self.clip_g = None
if t5:
dtype_t5 = comfy.model_management.pick_weight_dtype(dtype_t5, dtype, device)
self.t5xxl = T5XXLModel(device=device, dtype=dtype_t5)
self.t5xxl = T5XXLModel(device=device, dtype=dtype_t5, model_options=model_options)
self.dtypes.add(dtype_t5)
else:
self.t5xxl = None
@@ -81,7 +81,7 @@ class SD3ClipModel(torch.nn.Module):
def encode_token_weights(self, token_weight_pairs):
token_weight_pairs_l = token_weight_pairs["l"]
token_weight_pairs_g = token_weight_pairs["g"]
token_weight_pars_t5 = token_weight_pairs["t5xxl"]
token_weight_pairs_t5 = token_weight_pairs["t5xxl"]
lg_out = None
pooled = None
out = None
@@ -108,7 +108,7 @@ class SD3ClipModel(torch.nn.Module):
pooled = torch.cat((l_pooled, g_pooled), dim=-1)
if self.t5xxl is not None:
t5_out, t5_pooled = self.t5xxl.encode_token_weights(token_weight_pars_t5)
t5_out, t5_pooled = self.t5xxl.encode_token_weights(token_weight_pairs_t5)
if lg_out is not None:
out = torch.cat([lg_out, t5_out], dim=-2)
else:
@@ -132,6 +132,6 @@ class SD3ClipModel(torch.nn.Module):
def sd3_clip(clip_l=True, clip_g=True, t5=True, dtype_t5=None):
class SD3ClipModel_(SD3ClipModel):
def __init__(self, device="cpu", dtype=None):
super().__init__(clip_l=clip_l, clip_g=clip_g, t5=t5, dtype_t5=dtype_t5, device=device, dtype=dtype)
def __init__(self, device="cpu", dtype=None, model_options={}):
super().__init__(clip_l=clip_l, clip_g=clip_g, t5=t5, dtype_t5=dtype_t5, device=device, dtype=dtype, model_options=model_options)
return SD3ClipModel_