im running stable difusion on termux android and everything goes well till i tried to use loras and i have to update diffuser to 0.30 and now im getting this error:
File “/root/app.py”, line 1, in
from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
ImportError: cannot import name ‘EulerDiscreteScheduler’ from ‘diffusers’ (/root/.venv/lib/python3.11/site-packages/diffusers/init.py)
(.venv) root@localhost:~# nano app.py
(.venv) root@localhost:~# python3 app.py
Traceback (most recent call last):
File “/root/app.py”, line 1, in
from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
ImportError: cannot import name ‘EulerDiscreteScheduler’ from ‘diffusers’ (/root/.venv/lib/python3.11/site-packages/diffusers/init.py)
(.venv) root@localhost:~# nano app.py
(.venv) root@localhost:~#
Somebody knows what should i do?
Here more info:
I was trying to use this .py
from diffusers import StableDiffusionPipeline, EulerDiscreteScheduler
Use local models
model_id = “./stable-diffusion-v1-5”
Use Euler sampling
scheduler = EulerDiscreteScheduler.from_pretrained(model_id, subfolder=“scheduler”)
#scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
Enable low memory usage, set image size to 320x320 and steps to 50.
pipe = StableDiffusionPipeline.from_pretrained(model_id, scheduler=scheduler, low_cpu_mem_usage=True)
pipe.unet.load_attn_procs(“./Insertion.safetensors”, local_files_only=True)
Bypass NSFW filter
#pipe.safety_checker = lambda images, clip_input: (images, False)
pipe.safety_checker=None
pipe.feature_extractor=None
Prompts
prompt = “a roman soldier”
nprompt = “simple background, logo, anime, deformed, disfigured, poorly drawn, bad anatomy, wrong anatomy, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, blurry, amputation. tattoo, 3d animation (semi-realistic and anime and illustration and 3d rendering and drawing) deformations, mutant, old, disfigured, amputee, mutated, mutation, cropped, worst (((censored))), fat, long body, poorly drawn face, mole, pants,”
Start generating the
image = pipe(prompt, negative_prompt=nprompt, num_inference_steps=200, width=240, height=240).images[0]
Save the image
image.save(“result.png”)
pipe.enable_vae_tiling()
Im getting an error about eulerschedule but if i delete the eulerschedule i get this:
File “/root/app.py”, line 22, in
pipe.unet.load_attn_procs("./Insertion.safetensors", local_files_only=True)
File “/usr/local/lib/python3.11/dist-packages/diffusers/loaders.py”, line 366, in load_attn_procs attn_processor = getattr(attn_processor, sub_key)
File “/usr/local/lib/python3.11/dist-packages/diffusers/models/modeling_utils.py”, line 185, in getattr
return super().__getattr__(name)
^^^^^^^^^^^^^^^^^^^^^^^^^
File “/usr/local/lib/python3.11/dist-packages/torch/nn/modules/module.py”, line 1614, in getattr
raise AttributeError("'{}' object has no attribute '{}'".format(
```AttributeError: 'UNet2DConditionModel' object has no attribute ''
Can somebody help me please