mirrors/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2025-09-11 12:06:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add model_options for text encoder.

Browse Source
This commit is contained in:
comfyanonymous
2024-08-17 10:15:13 -04:00
parent 858d51f91a
commit fca42836f2
9 changed files with 66 additions and 57 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)

14
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):
@@ -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:

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}, 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)

16
comfy/text_encoders/sd3_clip.py
View File

@@ -8,9 +8,9 @@ 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={}):
@@ -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
@@ -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_