[Community Pipelines] K-Diffusion Pipeline #1360
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The documentation is not available anymore as the PR was closed or merged. |
2 tasks
pingren
reviewed
Nov 24, 2022
Comment on lines
+710
to
+728
|  | ||
|
|
||
| **K Diffusion**: | ||
| ```python | ||
| from diffusers import DiffusionPipeline, EulerDiscreteScheduler | ||
|
|
||
| seed = 33 | ||
|
|
||
| pipe = DiffusionPipeline.from_pretrained("CompVis/stable-diffusion-v1-4", custom_pipeline="sd_text2img_k_diffusion") | ||
| pipe.scheduler = EulerDiscreteScheduler.from_config(pipe.scheduler.config) | ||
| pipe = pipe.to("cuda") | ||
|
|
||
| pipe.set_sampler("sample_euler") | ||
| generator = torch.Generator(device="cuda").manual_seed(seed) | ||
| image = pipe(prompt, generator=generator, num_inference_steps=50).images[0] | ||
| ``` | ||
|
|
||
|  | ||
|
|
There was a problem hiding this comment.
I can't tell the visual difference of generated images in this README example:
I suppose there would be something different to compare?
Contributor
Author
There was a problem hiding this comment.
Hey @pingren,
All I wanted to show here is that it "works" 😅
There was a problem hiding this comment.
I saw this PR in v0.8 a release notes and want to see what's the new k-diffusion, and it confuses me by showing “almost identical” results of K-diffusion and original diffusion.
Do you like the idea to tweak the parameters and show the difference? Reduce steps from 50 to 20 will show visual differences significantly.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds a pipeline that supports k-diffusion