Skip to content

[ernie-image] use concrete Mistral3Model / Ministral3ForCausalLM types #13687

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

Open
akshan-main wants to merge 1 commit into
base: main
Choose a base branch
from
+8 −8
Open

[ernie-image] use concrete Mistral3Model / Ministral3ForCausalLM types #13687

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
10 changes: 5 additions & 5 deletions src/diffusers/modular_pipelines/ernie_image/encoders.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@
import json

import torch
from transformers import AutoModel, AutoModelForCausalLM, AutoTokenizer
from transformers import AutoTokenizer, Ministral3ForCausalLM, Mistral3Model

from ...configuration_utils import FrozenDict
from ...guiders import ClassifierFreeGuidance
Expand All @@ -38,7 +38,7 @@ def description(self) -> str:
@property
def expected_components(self) -> list[ComponentSpec]:
return [
ComponentSpec("pe", AutoModelForCausalLM),
ComponentSpec("pe", Ministral3ForCausalLM),
ComponentSpec("pe_tokenizer", AutoTokenizer),
]

Expand Down Expand Up @@ -83,7 +83,7 @@ def intermediate_outputs(self) -> list[OutputParam]:

@staticmethod
def _enhance_prompt(
pe: AutoModelForCausalLM,
pe: Ministral3ForCausalLM,
pe_tokenizer: AutoTokenizer,
prompt: str,
device: torch.device,
Expand Down Expand Up @@ -160,7 +160,7 @@ def description(self) -> str:
@property
def expected_components(self) -> list[ComponentSpec]:
return [
ComponentSpec("text_encoder", AutoModel),
ComponentSpec("text_encoder", Mistral3Model),
ComponentSpec("tokenizer", AutoTokenizer),
ComponentSpec(
"guider",
Expand Down Expand Up @@ -200,7 +200,7 @@ def intermediate_outputs(self) -> list[OutputParam]:

@staticmethod
def _encode(
text_encoder: AutoModel,
text_encoder: Mistral3Model,
tokenizer: AutoTokenizer,
prompt: list[str],
device: torch.device,
Expand Down
6 changes: 3 additions & 3 deletions src/diffusers/pipelines/ernie_image/pipeline_ernie_image.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@
from typing import Callable, List, Optional, Union

import torch
from transformers import AutoModel, AutoModelForCausalLM, AutoTokenizer
from transformers import AutoTokenizer, Ministral3ForCausalLM, Mistral3Model

from ...image_processor import VaeImageProcessor
from ...loaders import ErnieImageLoraLoaderMixin
Expand Down Expand Up @@ -52,10 +52,10 @@ def __init__(
self,
transformer: ErnieImageTransformer2DModel,
vae: AutoencoderKLFlux2,
text_encoder: AutoModel,
text_encoder: Mistral3Model,
tokenizer: AutoTokenizer,
scheduler: FlowMatchEulerDiscreteScheduler,
pe: Optional[AutoModelForCausalLM] = None,
pe: Optional[Ministral3ForCausalLM] = None,
pe_tokenizer: Optional[AutoTokenizer] = None,
):
super().__init__()
Expand Down
Loading