modelscope / modelscope/DiffSynth-Studio

ImportError: cannot import name 'SiglipVisionTransformer' from 'transformers.models.siglip.modeling_siglip'

Open
#1,407 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 12m
Merged PRs (30d)
45

Description

Traceback (most recent call last):
File "/workspace/vk_git_ws/DiffSynth-Studio/examples/qwen_image/model_training/train.py", line 3, in
from diffsynth.pipelines.qwen_image import QwenImagePipeline, ModelConfig
File "/workspace/vk_git_ws/DiffSynth-Studio/diffsynth/pipelines/qwen_image.py", line 19, in
from ..models.siglip2_image_encoder import Siglip2ImageEncoder
File "/workspace/vk_git_ws/DiffSynth-Studio/diffsynth/models/siglip2_image_encoder.py", line 1, in
from transformers.models.siglip.modeling_siglip import SiglipVisionTransformer, SiglipVisionConfig
ImportError: cannot import name 'SiglipVisionTransformer' from 'transformers.models.siglip.modeling_siglip' (/usr/local/lib/python3.11/dist-packages/transformers/models/siglip/modeling_siglip.py)

Reproduction Steps:

  1. Git clone repo
  2. pip install -e .
  3. chmod +x ./examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh
  4. ./examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh

In step 4, lora refinement I am getting the above error. I see another issue with the same error but it didn't help resolve.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with examples/qwen_image/model_training/train.py and reproduce the failure using examples/qwen_image/model_training/lora/Qwen-Image-Edit-2511.sh after pip install -e .. Trace the import through diffsynth/pipelines/qwen_image.py to diffsynth/models/siglip2_image_encoder.py and compare it with the installed transformers module. Done means the Qwen Image LoRA refinement command starts without this ImportError.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.