Qwen Image Edit Quantized Stopped working #12657
Description
Describe the bug
i have been using the qwen edit for a little while now an all of a sudden its crashing when i spin up my same docker conatiner on a new machine.
all with main branch of Diffusers from GitHub pulling fresh on spin up.
ive done hunreds of images with the same docker container that installs the libs and runs my same pipeline script... any ideas?
Reproduction
from diffusers import QwenImageEditPlusPipeline, FlowMatchEulerDiscreteScheduler, FlowMatchHeunDiscreteScheduler
import os, io, time, sys, json
from typing import Optional
import torch
from PIL import Image
from typing import List, Dict, Optional, Any
from utils import json_to_render, json_to_sampler_options, RenderStatus, assign_loras, callback_on_step_end, load_image_sources
model_name = "aifx-art/Qwen-Image-Edit-2509-Q4"
dtype = torch.bfloat16
Load quantized pipeline
pipeline = QwenImageEditPlusPipeline.from_pretrained(
#quantized_model_dir,
model_name,
torch_dtype=dtype,
)
print("Quantized pipeline loaded.")
pipeline.scheduler = FlowMatchEulerDiscreteScheduler.from_config(
pipeline.scheduler.config,
)
print("Scheduler", pipeline.scheduler)
Pick device (MPS for mac, CUDA for Linux/Windows with GPU)
if torch.backends.mps.is_available():
pipeline = pipeline.to("mps")
elif torch.cuda.is_available():
pipeline = pipeline.to("cuda")
else:
pipeline = pipeline.to("cpu")
pipeline.enable_model_cpu_offload()
pipeline.set_progress_bar_config(disable=None)
generator = None
if render.seed is not None:
generator = torch.Generator(device=pipeline.device).manual_seed(render.seed)
images = load_image_sources(render)
inputs = {
"image": images if images else None,
"prompt": render.pos,
"negative_prompt": render.neg,
"num_inference_steps": render.steps,
"generator": generator,
"num_images_per_prompt": 1,
"width": render.width,
"height": render.height,
"callback_on_step_end": callback_on_step_end,
"true_cfg_scale": render.guidance,
#"guidance_scale": 1.0,
}
with torch.inference_mode():
output = pipeline(**inputs)
output_image = output.images[0]
print("saving file",render.filename)
output_image.save(render.filename, format="PNG")
Logs
pipeline = QwenImageEditPlusPipeline.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File huggingface_hub/utils/_validators.py", line 89, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/diffusers/pipelines/pipeline_utils.py", line 1021, in from_pretrained
loaded_sub_model = load_sub_model(
^^^^^^^^^^^^^^^
File .venv/lib/python3.12/site-packages/diffusers/pipelines/pipeline_loading_utils.py", line 876, in load_sub_model
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 270, in _wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File .venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4122, in from_pretrained
model, missing_keys, unexpected_keys, mismatched_keys, offload_index, error_msgs = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/transformers/modeling_utils.py", line 4275, in _load_pretrained_model
missing_keys, unexpected_keys, mismatched_keys, misc = convert_and_load_state_dict_in_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File ".venv/lib/python3.12/site-packages/transformers/core_model_loading.py", line 621, in convert_and_load_state_dict_in_model
raise ValueError("This quantization method is gonna be supported SOOOON")
ValueError: This quantization method is gonna be supported SOOOONSystem Info
tried on an ADA 4000 and a RTX4090 and RTX 5090 all with main branch of Diffusers from GitHub,
Who can help?
No response