Comments (3)
if the program is crashing you must post a stack trace for me to help.
Ultimately if you want to use scripting to interact with the main program, you need to read the main program.
Samplers are in the global variable samplers
:
steps = [2,4,8,12]
sampler_index= [4,5,6,7]
#alternatively:
#sampler_index = [i for i, x in enumerate(samplers) if x.name in ['Euler a', 'Euler', 'LMS']]
def cell(x, y, p=p):
p.steps = x
p.sampler_index = y
return process_images(p).images[0]
images = [draw_xy_grid(
xs = steps,
ys = sampler_index,
x_label = lambda x: f'Steps = {x}',
y_label = lambda y: f'Sampler = {samplers[y].name}',
cell = cell
)]
save_image(images[0], 'test/asdf', 'asdf')
display(images)
Actually no need for crash log. I broke PLMS. It was crashing when you used PLMS.
from stable-diffusion-webui.
I'm attempting to modify the sampler/scale script to make something that outputs the example image above, but it's crashing when I try to run it.
For the few it does work on, it's unclear which sampler is which, would anyone be able to help please? -
steps = [20,40,80,120,240] sampler_index= [4,5,6,7] def cell(x, y, p=p): p.steps = x p.sampler_index = y return process_images(p).images[0] images = [draw_xy_grid( xs = steps, ys = sampler_index, x_label = lambda x: f'Steps = {x}', y_label = lambda y: f'CFG = {y}', cell = cell )] save_image(images[0], 'test/gnomeplot', 'gnome6') display(images)
If you need a quick reference, the actual order is :
0 : Euler Ancestral
1 : Euler
2 : LMS
3 : Heun
4 : DPM2
5 : DPM2 Ancestral
6 : DDIM
7 : PLMS
from stable-diffusion-webui.
if the program is crashing you must post a stack trace for me to help.
Ultimately if you want to use scripting to interact with the main program, you need to read the main program.
Samplers are in the global variable
samplers
:steps = [2,4,8,12] sampler_index= [4,5,6,7] #alternatively: #sampler_index = [i for i, x in enumerate(samplers) if x.name in ['Euler a', 'Euler', 'LMS']] def cell(x, y, p=p): p.steps = x p.sampler_index = y return process_images(p).images[0] images = [draw_xy_grid( xs = steps, ys = sampler_index, x_label = lambda x: f'Steps = {x}', y_label = lambda y: f'Sampler = {samplers[y].name}', cell = cell )] save_image(images[0], 'test/asdf', 'asdf') display(images)Actually no need for crash log. I broke PLMS. It was crashing when you used PLMS.
Not being a coder myself (in the slightest) it's a miracle that I got as far as I did but your example is exactly what I wanted so thank you so much.
from stable-diffusion-webui.
Related Issues (20)
- [Feature Request]: Add a scheduler pattern to the filename save options now that it has been removed from the sampler in 1.9.0 HOT 1
- [Bug]: AttributeError: 'NoneType' object has no attribute 'lowvram' HOT 3
- [Bug]: error while loading shared libraries: libstdc++.so.6: cannot open shared object file: No such file or directory
- [Bug]: Dev Branch 'KDiffusionSampler' object has no attribute 'trajectory_enable' HOT 2
- [Bug]: AttributeError: 'NoneType' object has no attribute 'lowvram' after BSOD HOT 1
- [Bug]: `get_crop_region_v2` error, when `Only masked padding, pixels` is set to 0 HOT 2
- [Bug]: AttributeError: 'NoneType' object has no attribute 'lowvram' HOT 8
- [Feature Request]: Please add support for the COSXL model by Stability AI HOT 1
- [Bug]: After upgrading to 1.9.0, you can't start it, you will report "Expected String or Bytes-Like Object" HOT 1
- [Bug]: No module named 'pillow_avif' HOT 2
- [Feature Request]: Backwards compatibility for txt2img and img2img API calls in 1.9.x versions
- AttributeError: 'UiControlNetUnit' object has no attribute 'enable'[Bug]: at last version HOT 10
- ERROR Calling AnimateDiff HOT 10
- [Bug]: Can't create venv at the first launch HOT 2
- RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument weight in method wrapper_CUDA___slow_conv2d_forward)[Bug]: HOT 2
- Torch is not able to see GPU HOT 6
- [Bug]: sd-webui-prompt-all-in-one extension is glitching the prompt bar HOT 2
- [Bug]: LORA's with .zip extension do not display in list with other LORA's HOT 1
- [Feature Request]: HOT 4
- [Feature Request]: Image Formats passed to api calls HOT 1
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 stable-diffusion-webui.