35 questions
0
votes
0
answers
78
views
How to solve device mismatch issue when using offloading with QwenImageEditPlus pipeline and GGUF weights
After failing to make the QwenImageEditPlus run (https://huggingface.co/spaces/discord-community/README/discussions/9#68d260e32053323e6bfab30c), I tried a different approach (thanks to all the example ...
- 1,215
1
vote
0
answers
294
views
Encountering an AttibuteError: module 'torch' has no attribute 'xpu'
I'm encountering an error
AttibuteError: module 'torch' has no attribute 'xpu'
when running the diffusers library in a Google Colab environment with a CUDA GPU. I'm trying to use DiffusionPipleline....
2
votes
1
answer
102
views
How to stop hugging face pipeline operation
I need to stop hugging face pipeline operation. I tried to achieve this using a method from the following question, but it didn't work. I set the breakpoint on the line return flag and expected ...
- 412
0
votes
1
answer
157
views
Is HuggingFace Accelerate's init_empty_weights Context Manager (Properly) Implemented for a Diffuser?
Discussion
HuggingFace accelerate's init_empty_weights() properly loads all text encoders I tested to the PyTorch meta device and consumes no apparent memory or disk space while loaded.
However, it ...
- 185
0
votes
0
answers
207
views
IP-adapter plus face model not working as expected
I came from these two links,
https://huggingface.co/h94/IP-Adapter-FaceID
https://stable-diffusion-art.com/consistent-face/
They all mentioned I can preserve face id with the controlnet model.
So I ...
- 23.7k
5
votes
1
answer
23k
views
ImportError: cannot import name 'cached_download' from 'huggingface_hub'
huggingface_hub==0.27.1
diffusers==0.28.0
I am getting this error:
Traceback (most recent call last): File "/data/om/Lotus/infer.py", line 11, in <module>
from diffusers.utils ...
- 1,067
0
votes
1
answer
2k
views
ModuleNotFoundError: No module named 'diffusers.models.unet_2d_blocks'
when I use the diffusers in the https://github.com/alvinliu0/HumanGaussian project, I got the error :
Traceback (most recent call last):
File "launch.py", line 239, in <module>
...
- 1
0
votes
0
answers
178
views
Diffusers pipeline Instant ID with Ipadapter
I want to use an implementation of InstantID with Ipadapter using Diffusers library.
So far I got :
import diffusers
from diffusers.utils import load_image
from diffusers.models import ControlNetModel
...
- 502
1
vote
1
answer
141
views
Differences in no of ResNet blocks in up blocks and no of channels for Unet2D model of diffusers
I have been reading about Unets and Stable diffusion and want to train one. I understand the original architecture for unets and how its channels, height and width evolve over down blocks and up ...
- 33
2
votes
1
answer
404
views
Huge memory consumption with SD3.5-medium
I have a g4dn.xlarge AWS GPU instance, it has 16GB memory + 48GB swap, and a Tesla T4 GPU Instance with 16GB vRAM.
According to the stability blog, it should be sufficient to run SD3.5 Medium model.
...
- 23.7k
0
votes
0
answers
397
views
Stable Diffusion 3.5 Turbo extremely slow using diffusers library
Running example code directly from the huggingface stable diffusion 3.5 site link and I am getting extremely slow run times, averaging 90 seconds per iteration. For reference when I use Stable ...
1
vote
1
answer
467
views
Cannot merge Lora weights back to the Flux Dev base model
I have a Flux-Dev base model which has been trained with the LoRA technique using the SimpleTuner framework (https://github.com/bghira/SimpleTuner/blob/main/documentation/quickstart/FLUX.md). The ...
- 21
0
votes
1
answer
810
views
Flux.1 Schnell image generator issue, GPU resources getting exhausted after 1 prompt
So, I tried to train a prompt based image generation model using FLUX.1-schnell. I used Lightning AI Studio (an alternate to Google Colab), that helped me to access to L40 GPU, that came with 48gb ...
4
votes
2
answers
2k
views
Issue loading FluxPipeline components
import torch
from diffusers import FluxPipeline
pipe = FluxPipeline.from_pretrained('C:\\Python\\Projects\\test1\\flux1dev', torch_dtype=torch.bfloat16)
pipe.enable_sequential_cpu_offload()
prompt = ...
- 41
1
vote
1
answer
321
views
Shapes mismatch while training diffusers/UNet2DConditionModel
I am trying to train diffusers/UNet2DConditionModel from scratch. Currently I have error on unet forwarding: mat1 and mat2 shapes cannot be multiplied (288x512 and 1280x512). I noticed that mat1 first ...
- 11
1
vote
1
answer
925
views
Stable Diffusion 3 does not work with diffusers
I try to use Stable Diffusion 3 on my desktop.
But it doesn't work.
I make the test.py file, the file is mostly same as sample code on Hugging Face.
Difference is only about authentication. The sample ...
- 11
1
vote
0
answers
102
views
GPU out of memory using hugging face
Pytorch is throwing GPU out of memory error
this is the code
from diffusers import StableDiffusionControlNetPipeline, ControlNetModel, UniPCMultistepScheduler
from diffusers.utils import load_image
...
- 11
0
votes
1
answer
238
views
stabilityai/stable-cascade takes 7+ hours to generate an image
I am using this model: https://huggingface.co/stabilityai/stable-cascade
from diffusers import StableCascadeCombinedPipeline
print("LOADING MODEL")
pipe = StableCascadeCombinedPipeline....
- 3,522
0
votes
1
answer
84
views
Runtime Error: StableCascadeCombinedPipeline: Expected all tensors to be on the same device
In a nutshell: Attempting to pass an image into StableCascadeCombinedPipeline gives a runtime error complaining about tensors not all being in cuda. The app works perfectly if I comment out the image ...
- 1,330
2
votes
0
answers
461
views
How to use batch prediction in Diffusers.StableDiffusionXLImg2ImgPipeline library
I'm currently exploring the StableDiffusion Image to Image library within HuggingFace. My goal is to generate images similar to the ones I have stored in a folder. Currently, I'm using the following ...
- 1,931
-1
votes
1
answer
439
views
How does the diffusers progress bar work?
I'm upscaling an image using StableDiffusionUpscalePipeline, but the second timestamp does not appear to be total estimated duration after all. What is it then and how to get a useful estimate?
...
- 20.3k
1
vote
0
answers
397
views
When I ｗant use "ControlNetModel.from_single_file" in diffuser, I give it correct path , but it doesn't work
code
from diffusers import StableDiffusionControlNetPipeline ,ControlNetModel
import torch
import cv2
img = cv2.imread('/home/leo/blues.png')
controlnet_model_path = "/mnt/d/models/...
- 11
3
votes
3
answers
3k
views
Generating preview images with Stable Diffusion XL pipeline results in black images
I'm working with the Stable Diffusion XL (SDXL) model from Hugging Face's diffusers library and encountering an issue where my callback function, intended to generate preview images during the ...
- 105
1
vote
0
answers
507
views
How to change the text_encoder for a Stable Diffusion model for fine-tuning?
I want to use Stable Diffusion model weights to generate class-conditional images- however, I don't want these images to be conditional on a text prompt, but rather on a number of binary class ...
-2
votes
1
answer
793
views
I use Diffusers to train LoRA. Training images are my photos, but the result image is not like me
Here is my training code.
from accelerate.utils import write_basic_config
write_basic_config()
import os
os.environ["MODEL_NAME"] = "runwayml/stable-diffusion-v1-5"
os.environ[&...
- 1,436
0
votes
1
answer
650
views
How to generate images with the same seed but with different kind of noise schedulers using Diffusers
I'm trying to use the Diffusers library to generate images with different schedulers (Just generate images I don't want to have to prompt).
For this I follow this tutorial: https://huggingface.co/docs/...
- 1
1
vote
0
answers
110
views
How to wipe gradients from UNet2DConditionModel
I am working with the "CompVis/ldm-text2im-large-256" building on top of the prompt-to-prompt code.
model = DiffusionPipeline.from_pretrained(model_id, height=IMAGE_RES, width=IMAGE_RES).to(...
- 295
1
vote
1
answer
2k
views
cannot import name 'AutoPipelineForText2Imag' from 'diffusers
I am trying to run a hugging face AI model, which gives me an error when I try to import the Diffuser module.
From here, I take this model, Huggingface Text to image generation model
Error log:
...
- 115
1
vote
1
answer
1k
views
RAM won't clear (diffusers)
I'm writing a script that needs to change models sometimes (diffusers & llama-cpp-python)
I don't have much RAM and VRAM, so I need to clean RAM and VRAM after using a model.
llama is fine, I just ...
- 11
0
votes
1
answer
1k
views
Diffusers bug: "UNet2DConditionModel" has no attribute "weight"
When using the official script "convert_lora_safetensor_to_diffusers.py", I tried to load a basemodel by using pipeline = StableDiffusionPipeline.from_pretrained(base_model_path, ...
- 1
1
vote
0
answers
486
views
How VAE and UNet sample size work in HF Diffusers?
Does anyone know how sample size work in SD's VAE and UNet?
All I know is the SD v1.5 was trained with 512*512, so it can generate 512*512 more properly. But when I set the pipeline like 384*384 or ...
- 11
-1
votes
1
answer
3k
views
stabilityai/stable-diffusion-2-1-base does not appear to have a file named scheduler_config.json
python preprocess.py --data_path data/horse.jpg --inversion_prompt 'A black horse runs in the sand'
Traceback (most recent call last):
File "/data1/wz/anaconda3/envs/pnp-diffusers/lib/python3.9/...
- 1
1
vote
2
answers
3k
views
Adding multiple LoRa safetensors to my HuggingFace model in Python
Suppose I use this script to load one fine-tuned model: (example taken from https://towardsdatascience.com/hugging-face-diffusers-can-correctly-load-lora-now-a332501342a3)
import torch
from diffusers ...
- 1,960
2
votes
0
answers
567
views
SDXL requires_aesthetics_score=True error
I'm trying to figure this one out, been at it for a while and can't seem to make any headway. Any help is greatly appreciated!!! It is my first time using Stable Diffusion so maybe I'm missing ...
- 330
11
votes
5
answers
36k
views
How to fix nsfw error for stable diffusion?
I always get the "Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed." error when using stable ...
- 111