[SDXL Turbo] Add some docs #5982
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. |
kashif
reviewed
Nov 29, 2023
|
|
||
| # SDXL Turbo | ||
|
|
||
| Stable Diffusion XL (SDXL) Turbo was proposed in [Adversarial Diffusion Distillation](https://stability.ai/research/adversarial-diffusion-distillation) by Axel Sauer Dominik Lorenz Andreas Blattmann Robin Rombach. |
Contributor
There was a problem hiding this comment.
Suggested change
| Stable Diffusion XL (SDXL) Turbo was proposed in [Adversarial Diffusion Distillation](https://stability.ai/research/adversarial-diffusion-distillation) by Axel Sauer Dominik Lorenz Andreas Blattmann Robin Rombach. | |
| Stable Diffusion XL (SDXL) Turbo was proposed in [Adversarial Diffusion Distillation](https://stability.ai/research/adversarial-diffusion-distillation) by Axel Sauer, Dominik Lorenz, Andreas Blattmann, and Robin Rombach. |
pcuenca
approved these changes
Nov 29, 2023
|
|
||
| ```py | ||
| # uncomment to install the necessary libraries in Colab | ||
| #!pip install -q diffusers transformers accelerate omegaconf |
Member
There was a problem hiding this comment.
Suggested change
| #!pip install -q diffusers transformers accelerate omegaconf | |
| #!pip install -q diffusers transformers accelerate |
Is omegaconf required?
Contributor
Author
There was a problem hiding this comment.
Yeah think it's in order to load the single file format - @DN6 we should probs try to not have it be required
| import torch | ||
|
|
||
| pipeline = StableDiffusionXLPipeline.from_single_file( | ||
| "https://huggingface.co/stabilityai/sdxl-turbo/blob/main/sd_xl_turbo_1.0_fp16.safetensors", torch_dtype=torch.float16, variant="fp16") |
Member
There was a problem hiding this comment.
Do we have to use the variant when we specify the full filename?
| ``` | ||
|
|
||
| <div class="flex justify-center"> | ||
| <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl-turbo-text2img.png" alt="generated image of an astronaut in a jungle"/> |
| ``` | ||
|
|
||
| <div class="flex justify-center"> | ||
| <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl-turbo-text2img.png" alt="generated image of an astronaut in a jungle"/> |
Member
There was a problem hiding this comment.
Suggested change
| <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl-turbo-text2img.png" alt="generated image of an astronaut in a jungle"/> | |
| <img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/sdxl-turbo-text2img.png" alt="generated image with SDXL Turbo"/> |
|
|
||
| ## Speed-up SDXL Turbo even more | ||
|
|
||
| TODO |
Member
There was a problem hiding this comment.
Suggested change
| TODO | |
| - Compile the UNet if you are using PyTorch version 2 or better. The first inference run will be very slow, but subsequent ones will be much faster. | |
| ```py | |
| pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True) |
- When using the default VAE, keep it in
float32to avoid costlydtypeconversions before and after each generation. You only need to do this one before your first generation:
pipe.upcast_vae()As an alternative, you can also use a 16-bit VAE created by community member @madebyollin that does not need to be upcasted to float32.
Co-authored-by: Pedro Cuenca <[email protected]>
AmericanPresidentJimmyCarter
pushed a commit
to AmericanPresidentJimmyCarter/diffusers
that referenced
this pull request
Apr 26, 2024
* add diffusers example * add diffusers example * Comment about making it faster * Apply suggestions from code review Co-authored-by: Pedro Cuenca <[email protected]> --------- Co-authored-by: Pedro Cuenca <[email protected]>
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.
What does this PR do?
Adds some docs for SDXL Turbo