Skip to content

Use T5Tokenizer instead of MT5Tokenizer (removed in Transformers v5.0+) #12877

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
yiyixuxu merged 1 commit into from
Dec 23, 2025
Merged

Use T5Tokenizer instead of MT5Tokenizer (removed in Transformers v5.0+) #12877

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions examples/community/pipeline_hunyuandit_differential_img2img.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,8 @@
BertModel,
BertTokenizer,
CLIPImageProcessor,
MT5Tokenizer,
T5EncoderModel,
T5Tokenizer,
)

from diffusers.callbacks import MultiPipelineCallbacks, PipelineCallback
Expand Down Expand Up @@ -260,7 +260,7 @@ class HunyuanDiTDifferentialImg2ImgPipeline(DiffusionPipeline):
The HunyuanDiT model designed by Tencent Hunyuan.
text_encoder_2 (`T5EncoderModel`):
The mT5 embedder. Specifically, it is 't5-v1_1-xxl'.
tokenizer_2 (`MT5Tokenizer`):
tokenizer_2 (`T5Tokenizer`):
The tokenizer for the mT5 embedder.
scheduler ([`DDPMScheduler`]):
A scheduler to be used in combination with HunyuanDiT to denoise the encoded image latents.
Expand Down Expand Up @@ -295,7 +295,7 @@ def __init__(
feature_extractor: CLIPImageProcessor,
requires_safety_checker: bool = True,
text_encoder_2=T5EncoderModel,
tokenizer_2=MT5Tokenizer,
tokenizer_2=T5Tokenizer,
):
super().__init__()

Expand Down
6 changes: 3 additions & 3 deletions src/diffusers/pipelines/controlnet_hunyuandit/pipeline_hunyuandit_controlnet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

import numpy as np
import torch
from transformers import BertModel, BertTokenizer, CLIPImageProcessor, MT5Tokenizer, T5EncoderModel
from transformers import BertModel, BertTokenizer, CLIPImageProcessor, T5EncoderModel, T5Tokenizer

from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput

Expand Down Expand Up @@ -185,7 +185,7 @@ class HunyuanDiTControlNetPipeline(DiffusionPipeline):
The HunyuanDiT model designed by Tencent Hunyuan.
text_encoder_2 (`T5EncoderModel`):
The mT5 embedder. Specifically, it is 't5-v1_1-xxl'.
tokenizer_2 (`MT5Tokenizer`):
tokenizer_2 (`T5Tokenizer`):
The tokenizer for the mT5 embedder.
scheduler ([`DDPMScheduler`]):
A scheduler to be used in combination with HunyuanDiT to denoise the encoded image latents.
Expand Down Expand Up @@ -229,7 +229,7 @@ def __init__(
HunyuanDiT2DMultiControlNetModel,
],
text_encoder_2: Optional[T5EncoderModel] = None,
tokenizer_2: Optional[MT5Tokenizer] = None,
tokenizer_2: Optional[T5Tokenizer] = None,
requires_safety_checker: bool = True,
):
super().__init__()
Expand Down
6 changes: 3 additions & 3 deletions src/diffusers/pipelines/hunyuandit/pipeline_hunyuandit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

import numpy as np
import torch
from transformers import BertModel, BertTokenizer, CLIPImageProcessor, MT5Tokenizer, T5EncoderModel
from transformers import BertModel, BertTokenizer, CLIPImageProcessor, T5EncoderModel, T5Tokenizer

from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput

Expand Down Expand Up @@ -169,7 +169,7 @@ class HunyuanDiTPipeline(DiffusionPipeline):
The HunyuanDiT model designed by Tencent Hunyuan.
text_encoder_2 (`T5EncoderModel`):
The mT5 embedder. Specifically, it is 't5-v1_1-xxl'.
tokenizer_2 (`MT5Tokenizer`):
tokenizer_2 (`T5Tokenizer`):
The tokenizer for the mT5 embedder.
scheduler ([`DDPMScheduler`]):
A scheduler to be used in combination with HunyuanDiT to denoise the encoded image latents.
Expand Down Expand Up @@ -204,7 +204,7 @@ def __init__(
feature_extractor: CLIPImageProcessor,
requires_safety_checker: bool = True,
text_encoder_2: Optional[T5EncoderModel] = None,
tokenizer_2: Optional[MT5Tokenizer] = None,
tokenizer_2: Optional[T5Tokenizer] = None,
):
super().__init__()

Expand Down
6 changes: 3 additions & 3 deletions src/diffusers/pipelines/pag/pipeline_pag_hunyuandit.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@

import numpy as np
import torch
from transformers import BertModel, BertTokenizer, CLIPImageProcessor, MT5Tokenizer, T5EncoderModel
from transformers import BertModel, BertTokenizer, CLIPImageProcessor, T5EncoderModel, T5Tokenizer

from diffusers.pipelines.stable_diffusion import StableDiffusionPipelineOutput

Expand Down Expand Up @@ -173,7 +173,7 @@ class HunyuanDiTPAGPipeline(DiffusionPipeline, PAGMixin):
The HunyuanDiT model designed by Tencent Hunyuan.
text_encoder_2 (`T5EncoderModel`):
The mT5 embedder. Specifically, it is 't5-v1_1-xxl'.
tokenizer_2 (`MT5Tokenizer`):
tokenizer_2 (`T5Tokenizer`):
The tokenizer for the mT5 embedder.
scheduler ([`DDPMScheduler`]):
A scheduler to be used in combination with HunyuanDiT to denoise the encoded image latents.
Expand Down Expand Up @@ -208,7 +208,7 @@ def __init__(
feature_extractor: Optional[CLIPImageProcessor] = None,
requires_safety_checker: bool = True,
text_encoder_2: Optional[T5EncoderModel] = None,
tokenizer_2: Optional[MT5Tokenizer] = None,
tokenizer_2: Optional[T5Tokenizer] = None,
pag_applied_layers: Union[str, List[str]] = "blocks.1", # "blocks.16.attn1", "blocks.16", "16", 16
):
super().__init__()
Expand Down
Loading