Comments (10)
Hi, sorry I deleted my answer 'cause the link didn't work in github for some reason. (?) The model checkpoints are download-able in the Hugginface model card.
Anyways your error is because you're calling both scripts/gradio/inpainting.py and scripts/gradio/superresolution.py. You should run:
!python scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml x4-upscaler-ema.ckpt
for upscaling.
I ran into the same issue and I guess there might have been a mistake in the README yesterday ?
Hope this helps
from stablediffusion.
Thank you for answering!
I'll try!
from stablediffusion.
Hi, sorry I deleted my answer 'cause the link didn't work in github for some reason. (?) The model checkpoints are download-able in the Hugginface model card. Anyways your error is because you're calling both scripts/gradio/inpainting.py and scripts/gradio/superresolution.py. You should run:
!python scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml x4-upscaler-ema.ckpt
for upscaling. I ran into the same issue and I guess there might have been a mistake in the README yesterday ? Hope this helps
Is it possible to use the upscaler on our own images, and not have to first generate SD images?
from stablediffusion.
Thank you for answering.
I want to upscale a local image. Is upscaling possible even if the image is not generated by SD?
from stablediffusion.
Using the code you gave me below, I was able to start inference.
!python scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml x4-upscaler-ema.ckpt
However, even after 30 minutes or more, it does not proceed from the following display.
●log
No module 'xformers'. Proceeding without it.
LatentUpscaleDiffusion: Running in v-prediction mode
DiffusionWrapper has 473.40 M params.
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 64, 64) = 16384 dimensions.
making attention of type 'vanilla' with 512 in_channels
Downloading: 100% 3.94G/3.94G [01:11<00:00, 55.5MB/s]
/usr/local/lib/python3.7/dist-packages/gradio/deprecation.py:44: UserWarning: You have unused kwarg parameters in Number, please remove them: {'min': 0.0, 'max': 1.0}
f"You have unused kwarg parameters in {cls}, please remove them: {kwargs}"
/usr/local/lib/python3.7/dist-packages/gradio/deprecation.py:44: UserWarning: You have unused kwarg parameters in Number, please remove them: {'min': 0, 'max': 350, 'step': 1}
f"You have unused kwarg parameters in {cls}, please remove them: {kwargs}"
Running on local URL: http://127.0.0.1:7860/
To create a public link, set `share=True` in `launch()`.
●gpu version(googlecolab free version gpu)
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Sun_Feb_14_21:12:58_PST_2021
Cuda compilation tools, release 11.2, V11.2.152
Build cuda_11.2.r11.2/compiler.29618528_0
●pytorch version
open-clip-torch 2.7.0
pytorch-lightning 1.4.2
torch 1.10.0
torchaudio 0.10.0
torchmetrics 0.6.0
torchsummary 1.5.1
torchtext 0.11.0
torchvision 0.10.1
Does it take this long?
If you know any improvement measures, could you tell me?
from stablediffusion.
Using the code you gave me below, I was able to start inference.
!python scripts/gradio/superresolution.py configs/stable-diffusion/x4-upscaling.yaml x4-upscaler-ema.ckpt
However, even after 30 minutes or more, it does not proceed from the following display.
●log
No module 'xformers'. Proceeding without it. LatentUpscaleDiffusion: Running in v-prediction mode DiffusionWrapper has 473.40 M params. making attention of type 'vanilla' with 512 in_channels Working with z of shape (1, 4, 64, 64) = 16384 dimensions. making attention of type 'vanilla' with 512 in_channels Downloading: 100% 3.94G/3.94G [01:11<00:00, 55.5MB/s] /usr/local/lib/python3.7/dist-packages/gradio/deprecation.py:44: UserWarning: You have unused kwarg parameters in Number, please remove them: {'min': 0.0, 'max': 1.0} f"You have unused kwarg parameters in {cls}, please remove them: {kwargs}" /usr/local/lib/python3.7/dist-packages/gradio/deprecation.py:44: UserWarning: You have unused kwarg parameters in Number, please remove them: {'min': 0, 'max': 350, 'step': 1} f"You have unused kwarg parameters in {cls}, please remove them: {kwargs}" Running on local URL: http://127.0.0.1:7860/ To create a public link, set `share=True` in `launch()`.
●gpu version(googlecolab free version gpu)
nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2021 NVIDIA Corporation Built on Sun_Feb_14_21:12:58_PST_2021 Cuda compilation tools, release 11.2, V11.2.152 Build cuda_11.2.r11.2/compiler.29618528_0
●pytorch version
open-clip-torch 2.7.0 pytorch-lightning 1.4.2 torch 1.10.0 torchaudio 0.10.0 torchmetrics 0.6.0 torchsummary 1.5.1 torchtext 0.11.0 torchvision 0.10.1
Does it take this long? If you know any improvement measures, could you tell me?
Open this url: http://127.0.0.1:7860/ on your browser, then choose a image to run.
from stablediffusion.
Access is denied when opening http://127.0.0.1:7860/.
A screen with ERR_CONNECTION_REFUSED is displayed.
from stablediffusion.
I have an additional question.
I tried the demo below. Is this stable-diffusion 2.0?
https://huggingface.co/spaces/stabilityai/stable-diffusion-upscaler
from stablediffusion.
Access is denied when opening http://127.0.0.1:7860/.
A screen with ERR_CONNECTION_REFUSED is displayed.
I was able to get this to work using a public URL.
Thank you.
from stablediffusion.
@mule-engineer13 Hi, how did you get the http://127.0.0.1:7860/ work using a public URL, I also show this but my access is denied when opending it.
from stablediffusion.
Related Issues (20)
- Troubleshooting at installing Stable Diffusion HOT 2
- Do not change background
- The clip vision model that matches the clip text model in sd-2.1-base
- Stablediffusion HOT 1
- cant't clone at all HOT 3
- Are there vae encoder/decoder whose factors are 1, and 2?
- What is the encoding/color model for the SDXL latents?
- Question in paper: why the text-prompt embeding uses the penultimate text embeddings of a CLIP ViT-H/14 text-encoder?
- txt2img.py doesn't work. HOT 1
- Run "model.load_state_dict(sd, strict=False)" failed in txt2img.py HOT 1
- Using REST API Inpainting + Masking, is it possible? HOT 1
- After a several successful inferences, eventually a new inference with the same settings will crash due to allocating too much memory
- The result is not good as online website text2image HOT 1
- How SD process the strength parameter text such as "(amphibic:1.2)"? HOT 1
- Error on untimeError: Expected attn_mask dtype to be bool or to match query dtype, but got attn_mask.dtype: float and query.dtype: c10::BFloat16 instead. HOT 1
- torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 9.49 GiB. GPU 0 has a total capacty of 23.68 GiB of which 8.03 GiB is free. Including non-PyTorch memory, this process has 15.17 GiB memory in use. Of the allocated memory 14.73 GiB is allocated by PyTorch, and 133.53 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation. See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF HOT 1
- RuntimeError: Torch is not able to use GPU; add --skip-torch-cuda-test to COMMANDLINE_ARGS variable to disable this check HOT 1
- Continuous Drawing Issue in Picture-in-Picture Tab
- New HOT 1
- Stable diffusion
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from stablediffusion.