ahrm / unstablefusion Goto Github PK
View Code? Open in Web Editor NEWA Stable Diffusion desktop frontend with inpainting, img2img and more!
License: GNU General Public License v3.0
A Stable Diffusion desktop frontend with inpainting, img2img and more!
License: GNU General Public License v3.0
Hi there, I found this repo recently and after testing it a bit I fell in love with the way it works and the results you can get with it, Ive test other similar inpainting implementations but this one is pretty solid. One thing I did notice is the lack of scroll on the canvas or the area where the image is drawn/generated, with this tool it is possible to slowly create a huge image made in chunks with anything we want on it, not being able to scroll to the sides or up and down reduces the workable area we have and makes it so the size of what we can create is limited, if we had some scroll bars on the side or bottom part of the canvas so we can move it would be awesome and the possibilities with it are endless, even better would be to have a shortcut or something like middle mouse button for scrolling in the mouse direction, an extra thing that would be nice to have would be zooming in an out. I really hope some of these features could be added as it would improve things a lot. Thanks for your time, and thanks for making this :)
Can you provide instructions for using this without downloading the model from hugging faces?
I don't want to use my API key
Fetching 16 files: 100%|█████████████████████████████████████████████████████████████| 16/16 [00:00<00:00, 3181.27it/s]
Traceback (most recent call last):
File "unstablefusion.py", line 889, in handle_inpaint_button
inpainted_image = self.get_handler().inpaint(prompt,
File "unstablefusion.py", line 436, in get_handler
return self.stable_diffusion_manager.get_handler()
File "unstablefusion.py", line 318, in get_handler
return self.get_local_handler(self.get_huggingface_token())
File "unstablefusion.py", line 301, in get_local_handler
self.cached_local_handler = StableDiffusionHandler(token)
File "E:\AI\SD\SDUI\UnstableFusion-main\diffusionserver.py", line 27, in init
self.text2img = StableDiffusionPipeline.from_pretrained(
File "e:\Anaconda3\envs\ldm\lib\site-packages\diffusers\pipeline_utils.py", line 179, in to
module.to(torch_device)
File "e:\Anaconda3\envs\ldm\lib\site-packages\torch\nn\modules\module.py", line 907, in to
return self._apply(convert)
File "e:\Anaconda3\envs\ldm\lib\site-packages\torch\nn\modules\module.py", line 578, in _apply
module._apply(fn)
File "e:\Anaconda3\envs\ldm\lib\site-packages\torch\nn\modules\module.py", line 578, in _apply
module._apply(fn)
File "e:\Anaconda3\envs\ldm\lib\site-packages\torch\nn\modules\module.py", line 578, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "e:\Anaconda3\envs\ldm\lib\site-packages\torch\nn\modules\module.py", line 601, in apply
param_applied = fn(param)
File "e:\Anaconda3\envs\ldm\lib\site-packages\torch\nn\modules\module.py", line 905, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
File "e:\Anaconda3\envs\ldm\lib\site-packages\torch\cuda_init.py", line 210, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Just as listed - start the app, click the blank window anywhere. App freezes, app explodes. Implodes? Anyway, lol
Current commit is b7ae990 (If I did that right)
File "C:\Code\git\UnstableFusion\unstablefusion.py", line 633, in mousePressEvent
pos = self.window_to_image_point(e.pos())
File "C:\Code\git\UnstableFusion\unstablefusion.py", line 660, in window_to_image_point
return QPoint(new_x, new_y)
TypeError: arguments did not match any overloaded call:
QPoint(): too many arguments
QPoint(int, int): argument 1 has unexpected type 'float'
QPoint(QPoint): argument 1 has unexpected type 'float'```
$ python unstablefusion.py
QObject::moveToThread: Current thread (0x560370c73760) is not the object's thread (0x560374ec5b20).
Cannot move to target thread (0x560370c73760)
qt.qpa.plugin: Could not load the Qt platform plugin "xcb" in "/home/user/anaconda3/lib/python3.9/site-packages/cv2/qt/plugins" even though it was found.
This application failed to start because no Qt platform plugin could be initialized. Reinstalling the application may fix this problem.
Available platform plugins are: xcb, eglfs, linuxfb, minimal, minimalegl, offscreen, vnc, wayland-egl, wayland, wayland-xcomposite-egl, wayland-xcomposite-glx, webgl.
Aborted (core dumped)
This is a minor improvement but sometimes we might just want to start over and remove everything on the canvas, unless I missed the option for it right now we can only either manually erase everything on the canvas or restart the app which will unload the model in memory, a button to clear the canvas and start over would be a nice feature to have, a few other things that would be awesome to have would be making it so the inference/generation runs on a different thread so the GUI doesn't get blocked and unresponsive, this could potentially make it so we can update the image as its being generated, also, would be nice to have a button to stop the generation in case we accidentally started it when we didn't mean to or when we think it will take too long and we need to adjust some options and then rerun it.
Getting this error immediately after running python unstablefusion.py
, gui is still loaded:
/home/user/anaconda3/lib/python3.9/site-packages/torch/cuda/__init__.py:88: UserWarning: CUDA initialization: CUDA unknown error - this may be due to an incorrectly set up environment, e.g. changing env variable CUDA_VISIBLE_DEVICES after program start. Setting the available devices to be zero. (Triggered internally at /opt/conda/conda-bld/pytorch_1665040357079/work/c10/cuda/CUDAFunctions.cpp:109.)
return torch._C._cuda_getDeviceCount() > 0
/home/user/anaconda3/lib/python3.9/site-packages/scipy/__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.23.3
warnings.warn(f"A NumPy version >={np_minversion} and <{np_maxversion}"
and this one after hitting "Generate":
Fetching 16 files: 100%|███████████████████████████████████| 16/16 [00:00<00:00, 79512.87it/s]
Traceback (most recent call last):
File "/home/user/Developer/UnstableFusion/unstablefusion.py", line 856, in handle_generate_button
image = self.get_handler().generate(prompt,
File "/home/user/Developer/UnstableFusion/unstablefusion.py", line 436, in get_handler
return self.stable_diffusion_manager.get_handler()
File "/home/user/Developer/UnstableFusion/unstablefusion.py", line 318, in get_handler
return self.get_local_handler(self.get_huggingface_token())
File "/home/user/Developer/UnstableFusion/unstablefusion.py", line 301, in get_local_handler
self.cached_local_handler = StableDiffusionHandler(token)
File "/home/user/Developer/UnstableFusion/diffusionserver.py", line 27, in __init__
self.text2img = StableDiffusionPipeline.from_pretrained(
File "/home/user/anaconda3/lib/python3.9/site-packages/diffusers/pipeline_utils.py", line 179, in to
module.to(torch_device)
File "/home/user/anaconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 987, in to
return self._apply(convert)
File "/home/user/anaconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 639, in _apply
module._apply(fn)
File "/home/user/anaconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 639, in _apply
module._apply(fn)
File "/home/user/anaconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 639, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "/home/user/anaconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 662, in _apply
param_applied = fn(param)
File "/home/user/anaconda3/lib/python3.9/site-packages/torch/nn/modules/module.py", line 985, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
File "/home/user/anaconda3/lib/python3.9/site-packages/torch/cuda/__init__.py", line 227, in _lazy_init
torch._C._cuda_init()
RuntimeError: CUDA unknown error - this may be due to an incorrectly set up environment, e.g. changing env variable CUDA_VISIBLE_DEVICES after program start. Setting the available devices to be zero.
nvidia-smi
output:+-----------------------------------------------------------------------------+
| NVIDIA-SMI 520.61.05 Driver Version: 520.61.05 CUDA Version: 11.8 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... On | 00000000:01:00.0 On | N/A |
| 44% 59C P0 106W / 350W | 4860MiB / 24576MiB | 14% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 2358 G /usr/lib/xorg/Xorg 3038MiB |
| 0 N/A N/A 2714 G /usr/bin/gnome-shell 442MiB |
| 0 N/A N/A 177728 G ...187800556795193677,131072 924MiB |
| 0 N/A N/A 177762 G ...AAAAAAAAA= --shared-files 125MiB |
| 0 N/A N/A 224062 G ...RendererForSitePerProcess 228MiB |
+-----------------------------------------------------------------------------+
conda list
output:# Name Version Build Channel
_libgcc_mutex 0.1 main
_openmp_mutex 5.1 1_gnu
anyio 3.5.0 py310h06a4308_0
argon2-cffi 21.3.0 pyhd3eb1b0_0
argon2-cffi-bindings 21.2.0 py310h7f8727e_0
asttokens 2.0.5 pyhd3eb1b0_0
attrs 21.4.0 pyhd3eb1b0_0
babel 2.9.1 pyhd3eb1b0_0
backcall 0.2.0 pyhd3eb1b0_0
beautifulsoup4 4.11.1 py310h06a4308_0
blas 1.0 mkl
bleach 4.1.0 pyhd3eb1b0_0
brotlipy 0.7.0 py310h7f8727e_1002
bzip2 1.0.8 h7b6447c_0
ca-certificates 2022.07.19 h06a4308_0
certifi 2022.9.24 py310h06a4308_0
cffi 1.15.1 py310h74dc2b5_0
charset-normalizer 2.0.4 pyhd3eb1b0_0
cryptography 37.0.1 py310h9ce1e76_0
cuda 11.7.1 0 nvidia
cuda-cccl 11.7.91 0 nvidia
cuda-command-line-tools 11.7.1 0 nvidia
cuda-compiler 11.7.1 0 nvidia
cuda-cudart 11.7.99 0 nvidia
cuda-cudart-dev 11.7.99 0 nvidia
cuda-cuobjdump 11.7.91 0 nvidia
cuda-cupti 11.7.101 0 nvidia
cuda-cuxxfilt 11.7.91 0 nvidia
cuda-demo-suite 11.8.86 0 nvidia
cuda-documentation 11.8.86 0 nvidia
cuda-driver-dev 11.7.99 0 nvidia
cuda-gdb 11.8.86 0 nvidia
cuda-libraries 11.7.1 0 nvidia
cuda-libraries-dev 11.7.1 0 nvidia
cuda-memcheck 11.8.86 0 nvidia
cuda-nsight 11.8.86 0 nvidia
cuda-nsight-compute 11.8.0 0 nvidia
cuda-nvcc 11.7.99 0 nvidia
cuda-nvdisasm 11.8.86 0 nvidia
cuda-nvml-dev 11.7.91 0 nvidia
cuda-nvprof 11.8.87 0 nvidia
cuda-nvprune 11.7.91 0 nvidia
cuda-nvrtc 11.7.99 0 nvidia
cuda-nvrtc-dev 11.7.99 0 nvidia
cuda-nvtx 11.7.91 0 nvidia
cuda-nvvp 11.8.87 0 nvidia
cuda-runtime 11.7.1 0 nvidia
cuda-sanitizer-api 11.8.86 0 nvidia
cuda-toolkit 11.7.1 0 nvidia
cuda-tools 11.7.1 0 nvidia
cuda-visual-tools 11.7.1 0 nvidia
dbus 1.13.18 hb2f20db_0
debugpy 1.5.1 py310h295c915_0
decorator 5.1.1 pyhd3eb1b0_0
defusedxml 0.7.1 pyhd3eb1b0_0
entrypoints 0.4 py310h06a4308_0
executing 0.8.3 pyhd3eb1b0_0
expat 2.4.9 h6a678d5_0
ffmpeg 4.2.2 h20bf706_0
fontconfig 2.13.1 h6c09931_0
freetype 2.11.0 h70c0345_0
gds-tools 1.4.0.31 0 nvidia
giflib 5.2.1 h7b6447c_0
glib 2.69.1 h4ff587b_1
gmp 6.2.1 h295c915_3
gnutls 3.6.15 he1e5248_0
gst-plugins-base 1.14.0 h8213a91_2
gstreamer 1.14.0 h28cd5cc_2
icu 58.2 he6710b0_3
idna 3.3 pyhd3eb1b0_0
intel-openmp 2021.4.0 h06a4308_3561
ipykernel 6.15.2 py310h06a4308_0
ipython 8.4.0 py310h06a4308_0
ipython_genutils 0.2.0 pyhd3eb1b0_1
ipywidgets 7.6.5 pyhd3eb1b0_1
jedi 0.18.1 py310h06a4308_1
jinja2 3.0.3 pyhd3eb1b0_0
jpeg 9e h7f8727e_0
json5 0.9.6 pyhd3eb1b0_0
jsonschema 4.16.0 py310h06a4308_0
jupyter 1.0.0 py310h06a4308_8
jupyter_client 7.3.5 py310h06a4308_0
jupyter_console 6.4.3 pyhd3eb1b0_0
jupyter_core 4.11.1 py310h06a4308_0
jupyter_server 1.18.1 py310h06a4308_0
jupyterlab 3.4.4 py310h06a4308_0
jupyterlab_pygments 0.1.2 py_0
jupyterlab_server 2.15.2 py310h06a4308_0
jupyterlab_widgets 1.0.0 pyhd3eb1b0_1
krb5 1.19.2 hac12032_0
lame 3.100 h7b6447c_0
lcms2 2.12 h3be6417_0
ld_impl_linux-64 2.38 h1181459_1
lerc 3.0 h295c915_0
libclang 10.0.1 default_hb85057a_2
libcublas 11.11.3.6 0 nvidia
libcublas-dev 11.11.3.6 0 nvidia
libcufft 10.9.0.58 0 nvidia
libcufft-dev 10.9.0.58 0 nvidia
libcufile 1.4.0.31 0 nvidia
libcufile-dev 1.4.0.31 0 nvidia
libcurand 10.3.0.86 0 nvidia
libcurand-dev 10.3.0.86 0 nvidia
libcusolver 11.4.1.48 0 nvidia
libcusolver-dev 11.4.1.48 0 nvidia
libcusparse 11.7.5.86 0 nvidia
libcusparse-dev 11.7.5.86 0 nvidia
libdeflate 1.8 h7f8727e_5
libedit 3.1.20210910 h7f8727e_0
libevent 2.1.12 h8f2d780_0
libffi 3.3 he6710b0_2
libgcc-ng 11.2.0 h1234567_1
libgomp 11.2.0 h1234567_1
libidn2 2.3.2 h7f8727e_0
libllvm10 10.0.1 hbcb73fb_5
libnpp 11.8.0.86 0 nvidia
libnpp-dev 11.8.0.86 0 nvidia
libnvjpeg 11.9.0.86 0 nvidia
libnvjpeg-dev 11.9.0.86 0 nvidia
libopus 1.3.1 h7b6447c_0
libpng 1.6.37 hbc83047_0
libpq 12.9 h16c4e8d_3
libsodium 1.0.18 h7b6447c_0
libstdcxx-ng 11.2.0 h1234567_1
libtasn1 4.16.0 h27cfd23_0
libtiff 4.4.0 hecacb30_0
libunistring 0.9.10 h27cfd23_0
libuuid 1.0.3 h7f8727e_2
libvpx 1.7.0 h439df22_0
libwebp 1.2.2 h55f646e_0
libwebp-base 1.2.2 h7f8727e_0
libxcb 1.15 h7f8727e_0
libxkbcommon 1.0.1 hfa300c1_0
libxml2 2.9.14 h74e7548_0
libxslt 1.1.35 h4e12654_0
lz4-c 1.9.3 h295c915_1
markupsafe 2.1.1 py310h7f8727e_0
matplotlib-inline 0.1.6 py310h06a4308_0
mistune 0.8.4 py310h7f8727e_1000
mkl 2021.4.0 h06a4308_640
mkl-service 2.4.0 py310h7f8727e_0
mkl_fft 1.3.1 py310hd6ae3a3_0
mkl_random 1.2.2 py310h00e6091_0
nbclassic 0.3.5 pyhd3eb1b0_0
nbclient 0.5.13 py310h06a4308_0
nbconvert 6.4.4 py310h06a4308_0
nbformat 5.5.0 py310h06a4308_0
ncurses 6.3 h5eee18b_3
nest-asyncio 1.5.5 py310h06a4308_0
nettle 3.7.3 hbbd107a_1
notebook 6.4.12 py310h06a4308_0
nsight-compute 2022.3.0.22 0 nvidia
nspr 4.33 h295c915_0
nss 3.74 h0370c37_0
numpy 1.23.1 py310h1794996_0
numpy-base 1.23.1 py310hcba007f_0
openh264 2.1.1 h4ff587b_0
openssl 1.1.1q h7f8727e_0
packaging 21.3 pyhd3eb1b0_0
pandocfilters 1.5.0 pyhd3eb1b0_0
parso 0.8.3 pyhd3eb1b0_0
pcre 8.45 h295c915_0
pexpect 4.8.0 pyhd3eb1b0_3
pickleshare 0.7.5 pyhd3eb1b0_1003
pillow 9.2.0 py310hace64e9_1
pip 22.2.2 py310h06a4308_0
ply 3.11 py310h06a4308_0
prometheus_client 0.14.1 py310h06a4308_0
prompt-toolkit 3.0.20 pyhd3eb1b0_0
prompt_toolkit 3.0.20 hd3eb1b0_0
psutil 5.9.0 py310h5eee18b_0
ptyprocess 0.7.0 pyhd3eb1b0_2
pure_eval 0.2.2 pyhd3eb1b0_0
pycparser 2.21 pyhd3eb1b0_0
pygments 2.11.2 pyhd3eb1b0_0
pyopenssl 22.0.0 pyhd3eb1b0_0
pyparsing 3.0.9 py310h06a4308_0
pyqt 5.15.7 py310h6a678d5_1
pyqt5-sip 12.11.0 pypi_0 pypi
pyrsistent 0.18.0 py310h7f8727e_0
pysocks 1.7.1 py310h06a4308_0
python 3.10.6 haa1d7c7_0
python-dateutil 2.8.2 pyhd3eb1b0_0
python-fastjsonschema 2.16.2 py310h06a4308_0
pytorch 1.14.0.dev20221009 py3.10_cpu_0 pytorch-nightly
pytorch-cuda 11.7 h67b0de4_0 pytorch-nightly
pytorch-mutex 1.0 cpu pytorch-nightly
pytz 2022.1 py310h06a4308_0
pyzmq 23.2.0 py310h6a678d5_0
qt-main 5.15.2 h327a75a_7
qt-webengine 5.15.9 hd2b0992_4
qtconsole 5.3.2 py310h06a4308_0
qtpy 2.2.0 py310h06a4308_0
qtwebkit 5.212 h4eab89a_4
readline 8.1.2 h7f8727e_1
requests 2.28.1 py310h06a4308_0
send2trash 1.8.0 pyhd3eb1b0_1
setuptools 63.4.1 py310h06a4308_0
sip 6.6.2 py310h6a678d5_0
six 1.16.0 pyhd3eb1b0_1
sniffio 1.2.0 py310h06a4308_1
soupsieve 2.3.1 pyhd3eb1b0_0
sqlite 3.39.3 h5082296_0
stack_data 0.2.0 pyhd3eb1b0_0
terminado 0.13.1 py310h06a4308_0
testpath 0.6.0 py310h06a4308_0
tk 8.6.12 h1ccaba5_0
toml 0.10.2 pyhd3eb1b0_0
torchaudio 0.13.0.dev20221009 py310_cpu pytorch-nightly
torchvision 0.15.0.dev20221009 py310_cpu pytorch-nightly
tornado 6.2 py310h5eee18b_0
traitlets 5.1.1 pyhd3eb1b0_0
typing-extensions 4.3.0 py310h06a4308_0
typing_extensions 4.3.0 py310h06a4308_0
tzdata 2022c h04d1e81_0
urllib3 1.26.11 py310h06a4308_0
wcwidth 0.2.5 pyhd3eb1b0_0
webencodings 0.5.1 py310h06a4308_1
websocket-client 0.58.0 py310h06a4308_4
wheel 0.37.1 pyhd3eb1b0_0
widgetsnbextension 3.5.2 py310h06a4308_0
x264 1!157.20191217 h7b6447c_0
xz 5.2.6 h5eee18b_0
zeromq 4.3.4 h2531618_0
zlib 1.2.12 h5eee18b_3
zstd 1.5.2 ha4553b6_0
Please advise!
P.S. Can I use the checkpoint I've got downloaded already?
It seems like the latest version of diffusers had some huge improvements on performance, I tried modifying the code to work with the latest diffusers and had partial success with doing so, I was able to get the generation working but not inpainting, I tested version 0.5.0 of diffusers and I was getting like 1.6it/s, then version 0.6.0 was giving me around 3-5it/s. What I did was just change the lines with ["sample"][0]
to [0][0]
like in
im = self.text2img(
prompt=prompt,
width=512,
height=512,
strength=strength,
num_inference_steps=steps,
guidance_scale=guidance_scale,
callback=callback,
negative_prompt=negative_prompt,
generator=self.get_generator(seed)
)["sample"][0]
I just replaced it to be
im = self.text2img(
prompt=prompt,
width=512,
height=512,
strength=strength,
num_inference_steps=steps,
guidance_scale=guidance_scale,
callback=callback,
negative_prompt=negative_prompt,
generator=self.get_generator(seed)
)[0][0]
This should return in theory the correct image but for some reason inpainting doesn't work, generation and reimaging do work tho, my guess is that the mask used for inpainting doesnt match the input image or the unet config, this is the error I get when I try to run inpainting with the modifications I mentioned before
ValueError: Incorrect configuration settings! The config of `pipeline.unet`: FrozenDict([('sample_size', 64), ('in_channels', 4),
('out_channels', 4), ('center_input_sample', False), ('flip_sin_to_cos', True), ('freq_shift', 0),
('down_block_types', ['CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'CrossAttnDownBlock2D', 'DownBlock2D']), ('up_block_types', ['UpBlock2D', 'CrossAttnUpBlock2D', 'CrossAttnUpBlock2D', 'CrossAttnUpBlock2D']), ('block_out_channels', [320, 640, 1280, 1280]),
('layers_per_block', 2), ('downsample_padding', 1), ('mid_block_scale_factor', 1), ('act_fn', 'silu'), ('norm_num_groups', 32), ('norm_eps',
1e-05), ('cross_attention_dim', 768), ('attention_head_dim', 8), ('_class_name', 'UNet2DConditionModel'), ('_diffusers_version', '0.6.0'),
('_name_or_path',
'C:\\Users\\ZeroCool\\.cache\\huggingface\\diffusers\\models--CompVis--stable-diffusion-v1-4\\snapshots\\a304b1ab1b59dd6c3ba9c40705c29c6de4144096\\unet')]) expects 4 but received `num_channels_latents`: 4 + `num_channels_mask`: 1 + `num_channels_masked_image`: 4 = 9.
Please verify the config of `pipeline.unet` or your `mask_image` or `image` input.
Hope this helps somehow to reduce the amount of stuff needed for adding support for the latest diffusers. Thanks for the time and have a good day.
I see you have no LICENSE file for this project. The default is copyright.
I would suggest releasing the code under the GPL-3.0-or-later or AGPL-3.0-or-later license so that others are encouraged to contribute changes back to your project.
So we don't need to paste it every time we open it?
I've been successfully running stable diffusion locally using Automatic1111's webui (https://github.com/AUTOMATIC1111/stable-diffusion-webui) and wanted to try your front end (which looks cool). So, I already have the weights downloaded and have tinkered with things like textual inversion which generate additional embedding models. When I try to run UnstableFusion, I am asked for a huggingface token, which I imagine means you are going to download the model weights again. Is there a way to just point your code at the weights I already have? Or, better yet, is there a way to treat Automatic's implementation as a backend hosted on localhost? There is all kinds of innovation which has been implemented there (increasing/decreasing attention, prompt switching partway through generation, etc) which it would be great to be able to take advantage of while still using your nice innovations on the front end.
I am getting the following error when attempting to generate (most recent commit, running locally, Ubuntu 22, python 3.9)
Generating with strength 0.75, steps 30, guidance_scale 7.5, seed -1
Traceback (most recent call last):
File "/home/adrian/UnstableFusion/unstablefusion.py", line 912, in handle_generate_button
image = self.get_handler().generate(prompt,
File "/home/adrian/UnstableFusion/diffusionserver.py", line 117, in generate
im = self.text2img(
File "/home/adrian/.local/lib/python3.9/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
TypeError: __call__() got an unexpected keyword argument 'strength'
This looks a little bit like #3 but protobuf
is already installed. Commenting out the strength=strength,
on diffusionserver.py:121 removes the error and allows image generation, but obviously disables an important parameter.
pip install -r requirements-localgpu-win64.txt
This is a very cool project, thank you for sharing!
Both locally and from the colab, I am given an error popup when trying to generate or inpaint. I am able to free-paint on the canvas with the cursor.
I'm running on Windows 10, ensured to have every dependency, and ran Conda Powershell as an admin.
An error I received when running the server:
DeprecationWarning: an integer is required (got type float). Implicit conversion to integers using int is deprecated, and may be removed in a future version of Python.
strength_slider.setValue(value)
I also have an issue with the Tool interface being too tall for my screen, but that's likely because I'm using an unusual resolution -- I doubt it is the cause, but thought it worth mentioning.
Thanks!
I'm usually running the app with Colab servers with great success. Now I'm getting an error in the notebook, when running this step UnstableFusion.diffusionserver import run_app
ImportError Traceback (most recent call last)
[<ipython-input-8-38e5886b075e>](https://localhost:8080/#) in <module>
----> 1 from UnstableFusion.diffusionserver import run_app
[/content/UnstableFusion/diffusionserver.py](https://localhost:8080/#) in <module>
4 from PIL import Image
5 from diffusers import StableDiffusionPipeline, StableDiffusionImg2ImgPipeline
----> 6 from diffusers import StableDiffusionInpaintPipelineLegacy
7
8 from torch import autocast
ImportError: cannot import name 'StableDiffusionInpaintPipelineLegacy' from 'diffusers' (/usr/local/lib/python3.7/dist-packages/diffusers/__init__.py)
If you click the "Load Modifiers" button before saving them the app crashes, I got the following error in console:
Traceback (most recent call last):
File "C:\Users\davic\Desktop\AI\UnstableFusion\unstablefusion.py", line 1129, in handle_load_modifiers
mods = load_modifiers()
File "C:\Users\davic\Desktop\AI\UnstableFusion\unstablefusion.py", line 51, in load_modifiers
with open(get_modifiers_path(), 'r') as infile:
FileNotFoundError: [Errno 2] No such file or directory: 'C:\\Users\\davic\\Desktop\\AI\\UnstableFusion\\modifiers.txt'
ERROR: Could not open requirements file: [Errno 2] No such file or directory: 'requirements-localgpu-win64.txt'
This repository is fantastic. Is there a zoom in/out shortkey somewhere? I can't find it in the shortkeys. There is a key for increase and decrease size but that will simply crop the image. When I open an image that is larger than my screen there is no way of moving out of the visible area. There is no scrollbar either.
C:\Users\ZeroCool22\Desktop\UnstableFusion\UnstableFusion>python unstablefusion.py
Traceback (most recent call last):
File "C:\Users\ZeroCool22\Desktop\UnstableFusion\UnstableFusion\unstablefusion.py", line 7, in <module>
from diffusionserver import StableDiffusionHandler
File "C:\Users\ZeroCool22\Desktop\UnstableFusion\UnstableFusion\diffusionserver.py", line 4, in <module>
from diffusers import StableDiffusionPipeline, StableDiffusionInpaintPipeline, StableDiffusionImg2ImgPipeline
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\__init__.py", line 26, in <module>
from .pipelines import DDIMPipeline, DDPMPipeline, KarrasVePipeline, LDMPipeline, PNDMPipeline, ScoreSdeVePipeline
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\pipelines\__init__.py", line 11, in <module>
from .latent_diffusion import LDMTextToImagePipeline
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\pipelines\latent_diffusion\__init__.py", line 6, in <module>
from .pipeline_latent_diffusion import LDMBertModel, LDMTextToImagePipeline
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\pipelines\latent_diffusion\pipeline_latent_diffusion.py", line 12, in <module>
from transformers.modeling_utils import PreTrainedModel
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\transformers\modeling_utils.py", line 75, in <module>
from accelerate import __version__ as accelerate_version
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\__init__.py", line 7, in <module>
from .accelerator import Accelerator
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\accelerator.py", line 33, in <module>
from .tracking import LOGGER_TYPE_TO_CLASS, GeneralTracker, filter_trackers
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\accelerate\tracking.py", line 34, in <module>
import wandb
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\__init__.py", line 26, in <module>
from wandb import sdk as wandb_sdk
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\sdk\__init__.py", line 9, in <module>
from .wandb_init import _attach, init # noqa: F401
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\sdk\wandb_init.py", line 30, in <module>
from . import wandb_login, wandb_setup
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\sdk\wandb_login.py", line 25, in <module>
from .wandb_settings import Settings, Source
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\sdk\wandb_settings.py", line 39, in <module>
from wandb.sdk.wandb_setup import _EarlyLogger
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\sdk\wandb_setup.py", line 22, in <module>
from . import wandb_manager, wandb_settings
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\sdk\wandb_manager.py", line 14, in <module>
from wandb.sdk.lib.proto_util import settings_dict_from_pbmap
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\sdk\lib\proto_util.py", line 6, in <module>
from wandb.proto import wandb_internal_pb2 as pb
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\proto\wandb_internal_pb2.py", line 15, in <module>
from wandb.proto import wandb_base_pb2 as wandb_dot_proto_dot_wandb__base__pb2
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\wandb\proto\wandb_base_pb2.py", line 36, in <module>
_descriptor.FieldDescriptor(
File "C:\Users\ZeroCool22\AppData\Local\Programs\Python\Python310\lib\site-packages\google\protobuf\descriptor.py", line 560, in __new__
_message.Message._CheckCalledFromGeneratedFile()
TypeError: Descriptors cannot not be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:
1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).
More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates
C:\Users\ZeroCool22\Desktop\UnstableFusion\UnstableFusion>
Not sure if it is an issue that could or should be solved.
Inpaint seem to be using image mask to draw-in parts of image that are transparent.
Despite that it changes already painted (non-transparent) parts of image too.
How to reproduce:
Expected result:
Observed result:
While using on regular images repeated Inpaint-s that cover same area seem to change contrast/saturation of previously painted parts.
How to reproduce:
Expected result:
Observed result:
Another easy way to get this result is to Generate anything and then Inpaint many times without changing selection. Doing Inpaint 10 times or so will turn almost any result into colorful noise.
As far as I was able to debug both of those are manifestations of same issue, maybe something to do with masking.
The full traceback is:
Traceback (most recent call last):
File "/home/pokemon343638/UnstableFusion-main/unstablefusion.py", line 897, in handle_generate_button
if type(self.get_handler()) == ServerStableDiffusionHandler:
File "/home/pokemon343638/UnstableFusion-main/unstablefusion.py", line 460, in get_handler
return self.stable_diffusion_manager.get_handler()
File "/home/pokemon343638/UnstableFusion-main/unstablefusion.py", line 329, in get_handler
return self.get_local_handler(self.get_huggingface_token())
File "/home/pokemon343638/UnstableFusion-main/unstablefusion.py", line 312, in get_local_handler
self.cached_local_handler = StableDiffusionHandler(token)
NameError: name 'StableDiffusionHandler' is not defined
Fetching 15 files: 100%
15/15 [00:00<00:00, 545.25it/s]
ValueError Traceback (most recent call last)
2 frames
/usr/local/lib/python3.8/dist-packages/diffusers/pipeline_utils.py in from_pretrained(cls, pretrained_model_name_or_path, **kwargs)
514 class_obj()
515
--> 516 raise ValueError(
517 f"The component {class_obj} of {pipeline_class} cannot be loaded as it does not seem to have"
518 f" any of the loading methods defined in {ALL_IMPORTABLE_CLASSES}."
ValueError: The component <class 'transformers.models.clip.image_processing_clip.CLIPImageProcessor'> of <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> cannot be loaded as it does not seem to have any of the loading methods defined in {'ModelMixin': ['save_pretrained', 'from_pretrained'], 'SchedulerMixin': ['save_config', 'from_config'], 'DiffusionPipeline': ['save_pretrained', 'from_pretrained'], 'OnnxRuntimeModel': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizer': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizerFast': ['save_pretrained', 'from_pretrained'], 'PreTrainedModel': ['save_pretrained', 'from_pretrained'], 'FeatureExtractionMixin': ['save_pretrained', 'from_pretrained']}.
C:\Users\ZeroCool22\Desktop\UnstableFusion\UnstableFusion>python unstablefusion.py
'NoneType' object has no attribute 'width'
'NoneType' object has no attribute 'width'
Traceback (most recent call last):
File "C:\Users\ZeroCool22\Desktop\UnstableFusion\UnstableFusion\unstablefusion.py", line 565, in mousePressEvent
top_left = QPoint(e.pos().x() - self.selection_rectangle_size[0] / 2, e.pos().y() - self.selection_rectangle_size[1] / 2)
TypeError: arguments did not match any overloaded call:
QPoint(): too many arguments
QPoint(int, int): argument 1 has unexpected type 'float'
QPoint(QPoint): argument 1 has unexpected type 'float'
C:\Users\ZeroCool22\Desktop\UnstableFusion\UnstableFusion>
And just doing a Click on the Canvas, gives an error too and close it by itself.
I am doing this with NO EXPERIENCE so pls just help get this working. I really wanna do ai art but this is getting annoying.
Traceback (most recent call last):
File "C:\Users\Fuck you microsoft\Documents\UnstableFusion-main\UnstableFusion.py", line 897, in handle_generate_button
if type(self.get_handler()) == ServerStableDiffusionHandler:
File "C:\Users\Fuck you microsoft\Documents\UnstableFusion-main\UnstableFusion.py", line 460, in get_handler
return self.stable_diffusion_manager.get_handler()
File "C:\Users\Fuck you microsoft\Documents\UnstableFusion-main\UnstableFusion.py", line 329, in get_handler
return self.get_local_handler(self.get_huggingface_token())
File "C:\Users\Fuck you microsoft\Documents\UnstableFusion-main\UnstableFusion.py", line 312, in get_local_handler
self.cached_local_handler = StableDiffusionHandler(token)
File "C:\Users\Fuck you microsoft\Documents\UnstableFusion-main\diffusionserver.py", line 36, in init
self.text2img = StableDiffusionPipeline.from_pretrained(
File "C:\Users\Fuck you microsoft\anaconda3\lib\site-packages\diffusers\pipeline_utils.py", line 516, in from_pretrained
raise ValueError(
ValueError: The component <class 'transformers.models.clip.feature_extraction_clip.CLIPFeatureExtractor'> of <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> cannot be loaded as it does not seem to have any of the loading methods defined in {'ModelMixin': ['save_pretrained', 'from_pretrained'], 'SchedulerMixin': ['save_config', 'from_config'], 'DiffusionPipeline': ['save_pretrained', 'from_pretrained'], 'OnnxRuntimeModel': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizer': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizerFast': ['save_pretrained', 'from_pretrained'], 'PreTrainedModel': ['save_pretrained', 'from_pretrained'], 'FeatureExtractionMixin': ['save_pretrained', 'from_pretrained']}.
OS: Arch Linux rolling
GPU: GTX 1660 SUPER
Driver: nvidia-520.56.06
CUDA: cuda-tools installed
Whenever I go to generate, it crashes on a CUDA error, as shown below. I have all dependencies listed plus a fair few others since it also pointed out I didn't have them. I'm using a local clone of v1.4 of the diffusion model renamed to v1.5 because the program wants to only accept a v1.5 folder despite it not being out for the public (as far as I can tell) and the HTTPX request fails when I go for the access key.
See terminal output below (the backslashes in the last line are to be ignored, interfered with code block):
$ python unstablefusion.py
Generating with strength 0.75, steps 30, guidance_scale 7.5, seed 889492
0%| | 0/31 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/home/meteo/UnstableFusion/unstablefusion.py", line 912, in handle_generate_button
image = self.get_handler().generate(prompt,
File "/home/meteo/UnstableFusion/diffusionserver.py", line 114, in generate
im = self.text2img(
File "/home/meteo/.local/lib/python3.10/site-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion.py", line 326, in __call__
noise_pred = self.unet(latent_model_input, t, encoder_hidden_states=text_embeddings).sample
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/diffusers/models/unet_2d_condition.py", line 296, in forward
sample, res_samples = downsample_block(
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/diffusers/models/unet_blocks.py", line 563, in forward
hidden_states = attn(hidden_states, context=encoder_hidden_states)
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/diffusers/models/attention.py", line 162, in forward
hidden_states = block(hidden_states, context=context)
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/diffusers/models/attention.py", line 213, in forward
hidden_states = self.ff(self.norm3(hidden_states)) + hidden_states
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/diffusers/models/attention.py", line 344, in forward
return self.net(hidden_states)
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/container.py", line 139, in forward
input = module(input)
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/diffusers/models/attention.py", line 362, in forward
hidden_states, gate = self.proj(hidden_states).chunk(2, dim=-1)
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/meteo/.local/lib/python3.10/site-packages/torch/nn/modules/linear.py", line 114, in forward
return F.linear(input, self.weight, self.bias)
RuntimeError: CUDA error: CUBLAS_STATUS_EXECUTION_FAILED when calling \`cublasGemmEx( handle, opa, opb, m, n, k, &falpha, a, CUDA_R_16F, lda, b, CUDA_R_16F, ldb, &fbeta, c, CUDA_R_16F, ldc, CUDA_R_32F, CUBLAS_GEMM_DFALT_TENSOR_OP)\`
Traceback (most recent call last):
File "/home/boi/.local/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 213, in hf_raise_for_status
response.raise_for_status()
File "/usr/lib/python3.10/site-packages/requests/models.py", line 1021, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 403 Client Error: Forbidden for url: https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/fp16/model_index.json
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/home/boi/.local/lib/python3.10/site-packages/diffusers/configuration_utils.py", line 228, in get_config_dict
config_file = hf_hub_download(
File "/home/boi/.local/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1053, in hf_hub_download
metadata = get_hf_file_metadata(
File "/home/boi/.local/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1359, in get_hf_file_metadata
hf_raise_for_status(r)
File "/home/boi/.local/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 254, in hf_raise_for_status
raise HfHubHTTPError(str(HTTPError), response=response) from e
huggingface_hub.utils._errors.HfHubHTTPError: <class 'requests.exceptions.HTTPError'> (Request ID: Nk1158C9LHrkTH1ybJVBC)
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/boi/UnstableFusion/unstablefusion.py", line 897, in handle_generate_button
if type(self.get_handler()) == ServerStableDiffusionHandler:
File "/home/boi/UnstableFusion/unstablefusion.py", line 460, in get_handler
return self.stable_diffusion_manager.get_handler()
File "/home/boi/UnstableFusion/unstablefusion.py", line 329, in get_handler
return self.get_local_handler(self.get_huggingface_token())
File "/home/boi/UnstableFusion/unstablefusion.py", line 312, in get_local_handler
self.cached_local_handler = StableDiffusionHandler(token)
File "/home/boi/UnstableFusion/diffusionserver.py", line 33, in init
self.text2img = StableDiffusionPipeline.from_pretrained(
File "/home/boi/.local/lib/python3.10/site-packages/diffusers/pipeline_utils.py", line 431, in from_pretrained
config_dict = cls.get_config_dict(
File "/home/boi/.local/lib/python3.10/site-packages/diffusers/configuration_utils.py", line 260, in get_config_dict
raise EnvironmentError(
OSError: There was a specific connection error when trying to load runwayml/stable-diffusion-v1-5:
<class 'requests.exceptions.HTTPError'> (Request ID: Nk1158C9LHrkTH1ybJVBC)
Hey there,
Unfortunately reimagine element stopped working
File "D:\AI\UnstableFusion-main\unstablefusion.py", line 767, in handle_reimagine_button
reimagined_image = self.get_handler().reimagine(prompt,
TypeError: ServerStableDiffusionHandler.reimagine() got an unexpected keyword argument 'strength'
(using newest collab link + package from github)
What i need to change here?
def dummy_safety_checker(self):
def check(images, *args, **kwargs):
return images, [False] * len(images)
For this?:
def dummy_safety_checker(self):
def check(images, *args, **kwargs):
return images, [True] * len(images)
Or there is something more i need to modify?
PD: I run it Locally, no on Collab.
Hi,
I LOVE where this project is going, and I want to do my best to give useful feedback that moves the project forward.
I did notice, that when opening really large images, there is no option zoom out. It is simply locked to the window size. Could you maybe add that in?
Thanks!
Not too sure why this is happening. Everything installed accordingly but the "Generate" fetches 15 files, the GPU spins up and then I get the log below.
Both stable-diffusion-v1-4 and 1-5 have been cloned through Huggingface.co and User Access token is pasted in the application.
Do I need to edit something to point towards the .ckpt model of Stable-Diffusion 1.4?
Fetching 15 files: 100%|█████████████████████████████████████████████████████████████| 15/15 [00:00<00:00, 7505.91it/s]
The config attributes {'clip_sample': False} were passed to PNDMScheduler, but are not expected and will be ignored. Please verify your scheduler_config.json configuration file.
Traceback (most recent call last):
File "C:\AI\UnstableFusion\unstablefusion.py", line 897, in handle_generate_button
if type(self.get_handler()) == ServerStableDiffusionHandler:
File "C:\AI\UnstableFusion\unstablefusion.py", line 460, in get_handler
return self.stable_diffusion_manager.get_handler()
File "C:\AI\UnstableFusion\unstablefusion.py", line 329, in get_handler
return self.get_local_handler(self.get_huggingface_token())
File "C:\AI\UnstableFusion\unstablefusion.py", line 312, in get_local_handler
self.cached_local_handler = StableDiffusionHandler(token)
File "C:\AI\UnstableFusion\diffusionserver.py", line 36, in init
self.text2img = StableDiffusionPipeline.from_pretrained(
File "C:\Users\Jeff\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\pipeline_utils.py", line 516, in from_pretrained
raise ValueError(
ValueError: The component <class 'transformers.models.clip.image_processing_clip.CLIPImageProcessor'> of <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> cannot be loaded as it does not seem to have any of the loading methods defined in {'ModelMixin': ['save_pretrained', 'from_pretrained'], 'SchedulerMixin': ['save_config', 'from_config'], 'DiffusionPipeline': ['save_pretrained', 'from_pretrained'], 'OnnxRuntimeModel': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizer': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizerFast': ['save_pretrained', 'from_pretrained'], 'PreTrainedModel': ['save_pretrained', 'from_pretrained'], 'FeatureExtractionMixin': ['save_pretrained', 'from_pretrained']}.
hello i have this error and i don't find how fix it:
Traceback (most recent call last):
File "/home/roza/Documents/UnstableFusion/unstablefusion.py", line 897, in handle_generate_button
if type(self.get_handler()) == ServerStableDiffusionHandler:
File "/home/roza/Documents/UnstableFusion/unstablefusion.py", line 460, in get_handler
return self.stable_diffusion_manager.get_handler()
File "/home/roza/Documents/UnstableFusion/unstablefusion.py", line 329, in get_handler
return self.get_local_handler(self.get_huggingface_token())
File "/home/roza/Documents/UnstableFusion/unstablefusion.py", line 312, in get_local_handler
self.cached_local_handler = StableDiffusionHandler(token)
File "/home/roza/Documents/UnstableFusion/diffusionserver.py", line 36, in __init__
self.text2img = StableDiffusionPipeline.from_pretrained(
File "/home/roza/Documents/UnstableFusion/Unstablefusion/UF/lib/python3.10/site-packages/diffusers/pipeline_utils.py", line 516, in from_pretrained
raise ValueError(
ValueError: The component <class 'transformers.models.clip.feature_extraction_clip.CLIPFeatureExtractor'> of <class 'diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline'> cannot be loaded as it does not seem to have any of the loading methods defined in {'ModelMixin': ['save_pretrained', 'from_pretrained'], 'SchedulerMixin': ['save_config', 'from_config'], 'DiffusionPipeline': ['save_pretrained', 'from_pretrained'], 'OnnxRuntimeModel': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizer': ['save_pretrained', 'from_pretrained'], 'PreTrainedTokenizerFast': ['save_pretrained', 'from_pretrained'], 'PreTrainedModel': ['save_pretrained', 'from_pretrained'], 'FeatureExtractionMixin': ['save_pretrained', 'from_pretrained']}.
thx for your help
Hello,
Installed all dependencies using pip install -r requirements.txt
but receive this error: AssertionError: Torch not compiled with CUDA enabled
I assume line 8 torch>=1.12.1
in the requirement.txt is incorrect and should be something like touch>=1.12.1=py38_cu113
. Haven't tested this yet nor I'm I confident those are the correct versions for a cuda compiled version of torch. Just posting incase you have a quicker answer!
Traceback (most recent call last):
File "unstablefusion.py", line 7, in
from diffusionserver import StableDiffusionHandler
File "E:\AI\SD\SDUI\UnstableFusion-main\diffusionserver.py", line 4, in
from diffusers import StableDiffusionPipeline, StableDiffusionInpaintPipeline, StableDiffusionImg2ImgPipeline
File "e:\ai\koi-main\diffusers\src\diffusers_init_.py", line 18, in
from .pipelines import DDIMPipeline, DDPMPipeline, KarrasVePipeline, LDMPipeline, PNDMPipeline, ScoreSdeVePipeline
File "e:\ai\koi-main\diffusers\src\diffusers\pipelines_init_.py", line 11, in
from .latent_diffusion import LDMTextToImagePipeline
File "e:\ai\koi-main\diffusers\src\diffusers\pipelines\latent_diffusion_init_.py", line 6, in
from .pipeline_latent_diffusion import LDMBertModel, LDMTextToImagePipeline
File "e:\ai\koi-main\diffusers\src\diffusers\pipelines\latent_diffusion\pipeline_latent_diffusion.py", line 12, in
from transformers.modeling_utils import PreTrainedModel
File "E:\Anaconda3\envs\ldm\lib\site-packages\transformers\modeling_utils.py", line 79, in
from accelerate import dispatch_model, infer_auto_device_map, init_empty_weights
File "E:\Anaconda3\envs\ldm\lib\site-packages\accelerate_init_.py", line 7, in
from .accelerator import Accelerator
File "E:\Anaconda3\envs\ldm\lib\site-packages\accelerate\accelerator.py", line 33, in
from .tracking import LOGGER_TYPE_TO_CLASS, GeneralTracker, filter_trackers
File "E:\Anaconda3\envs\ldm\lib\site-packages\accelerate\tracking.py", line 29, in
from torch.utils import tensorboard
File "E:\Anaconda3\envs\ldm\lib\site-packages\torch\utils\tensorboard_init_.py", line 10, in
from .writer import FileWriter, SummaryWriter # noqa: F401
File "E:\Anaconda3\envs\ldm\lib\site-packages\torch\utils\tensorboard\writer.py", line 9, in
from tensorboard.compat.proto.event_pb2 import SessionLog
File "E:\Anaconda3\envs\ldm\lib\site-packages\tensorboard\compat\proto\event_pb2.py", line 17, in
from tensorboard.compat.proto import summary_pb2 as tensorboard_dot_compat_dot_proto_dot_summary__pb2
File "E:\Anaconda3\envs\ldm\lib\site-packages\tensorboard\compat\proto\summary_pb2.py", line 17, in
from tensorboard.compat.proto import tensor_pb2 as tensorboard_dot_compat_dot_proto_dot_tensor__pb2
File "E:\Anaconda3\envs\ldm\lib\site-packages\tensorboard\compat\proto\tensor_pb2.py", line 16, in
from tensorboard.compat.proto import resource_handle_pb2 as tensorboard_dot_compat_dot_proto_dot_resource__handle__pb2
File "E:\Anaconda3\envs\ldm\lib\site-packages\tensorboard\compat\proto\resource_handle_pb2.py", line 16, in
from tensorboard.compat.proto import tensor_shape_pb2 as tensorboard_dot_compat_dot_proto_dot_tensor__shape__pb2
File "E:\Anaconda3\envs\ldm\lib\site-packages\tensorboard\compat\proto\tensor_shape_pb2.py", line 18, in
DESCRIPTOR = _descriptor.FileDescriptor(
TypeError: init() got an unexpected keyword argument 'serialized_options'
Hi, I'm the packager of Sioyek for Flathub and noticed this other super cool project of yours. It would be nice to have it in Flathub too, but Flathub has a policy to only build from a tag (so not from a commit or branch tip). So two questions:
Are you ok with publishing UnstableFusion in www.flathub.org ?
Are you planning to tag a release for UnstableFusion ?
Thanks :-) ,
Hi are this can work with adobe firefly api or any other service ? thanks.
I think I saw in several repos there is some initial restriction on size and some repos that remove it?
Is there such a limit and if so why is it there?Is it possible to easily remove it?
Overall I want my width height to be increased more.
I'm receiving an error when I try to generate, reimagine, or inpaint. This with the webui up and it is being pointed to the server address.
when i click any of those options, I receive this error in the console,
size = resp_data['image_size']
KeyError: 'image_size'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.