Lesson 9 official topic

There’s some noise in the image so i think i could have been stable diffusion :rofl:

1 Like

I do have them as far as I can tell (diffusers ‘0.4.1’ transformers ‘4.23.0’ and pytorch ‘1.12.1.post201’ and yet I am hitting RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (torch.cuda.HalfTensor) should be the same On the pipei2i command :frowning:

Edit: I should add that I started from a fresh conda environment

2 Likes

I created a PR to suggest a requirements.txt file that installs the dependencies you need to run the notebooks locally. You can find the PR here: Add requirements.txt file by dpoulopoulos · Pull Request #1 · fastai/diffusion-nbs · GitHub

7 Likes

I had the same issue for StableDiffusionImg2ImgPipeline. So I installed the diffusers library from the latest commit and the issue was solved for me.

pip install git+https://github.com/huggingface/diffusers.git@e895952816dc4a9a04d1d82fb5f8bdee59341c06

(If you are working on colab, restart the runtime after you run the above command)
Hope this solves your issue too.

Update: Diffusers version 0.4.2 has the fix for this issue. Install it by using the command pip install diffusers==0.4.2

4 Likes

I created a PR to suggest a requirements.txt file that installs the dependencies you need to run the notebooks locally. You can find the PR here: Add requirements.txt file by dpoulopoulos · Pull Request #1 · fastai/diffusion-nbs · GitHub

This was very helpful and came just in time as I was setting up here on a Windows machine. Thank you!

One thing to clarify for others: You’ll need to install fastai and jupyter (conda install jupyter) as well to run these as jupyter notebooks locally.

6 Likes

Yep, that did it. Thank you.

1 Like

I don’t understand pipe signature in:

num_rows,num_cols = 4,4
prompts = [prompt] * num_cols
images = concat(pipe(prompts, guidance_scale=g).images for g in [1.1,3,7,14])

pipe accepts a list of prompts but only one guidance_scale? In :hugs: documentation, I found how to create a StableDiffusionPipeline but couldn’t find its __init__ definition.

Type:

   ?? StableDiffusionPipeline

That will show you the source code. Generally fir bleeding edge stuff the docs won’t always have the latest info.

8 Likes

Image2ImageAnimation128
Lesson 9A was excellent @johnowhitaker - I took your colourful dance and added to my woodpecker picture - interesting transformations with the Image2Image section.

16 Likes

Thanks @brismith! What a trippy result :slight_smile:

3 Likes

@dpoulopoulos’s requirements.txt looks great! Takes a while to get the right combinations of cuda/torch/etc.
If anyone is working with Conda, I’m using this environment.yml file to get the notebook from Lesson 9 working (I think conda manages dependencies a bit better than pip)

7 Likes

interesting thing to dive deeper is that for steps 1 or 2 the resulting image is black. from my limited understanding i was expecting all noise …

6 Likes


^^
The ‘why predict the noise rather than the image’ discussion yesterday is one that is happening in the literature too. The ‘v objective’ here is getting popular as it seems to help stabilize training, and additional framings are being explored too. (This screenshot is from the ‘progressive distillation’ paper which Jeremy showed as the new work bringing down the required number of sampling steps - explainer video here if you want to hear me waffle through an attempted summary).
Give it a few days or weeks and it’s a safe bet the diffusers library will have something like a ‘model_prediction_type’ parameter for epsilon or v or x or … to handle these different parametrizations.

10 Likes

I was wondering if Jeremy kept the OneNote he used throughout the lecture, if so it might be nice to share it? It would act as a good aide memoir.

2 Likes

If I remember correctly the HF stable diffusion pipeline has a NSFW/Disturbing images filter on. If you used a prompt that some for any reason the filter thinks might be inappropriate, it will return a black image (in the original SD it would rickroll you :joy: ). Keep in mind that as any filter for these kind of things it can be overly aggressive so it is not alway obvious what is going on (e.g. last time I run into this it was filtering out anything related to “dead”, so a cat leaving a dead mouse on the door was blacked out)

5 Likes

i used prompt = “a photograph of an astronaut riding a horse”
steps 1 and 2 give black image, step 3 is noisy image…

Pretty sure that’s SFW :smiley: Then I have no idea.

1 Like

Safety checker in the diffusers library has a lot of False positives for NSFW detection.
You can disable the safety filter if you want.

pipe.safety_checker = lambda images, **kwargs: (images, False)
6 Likes

Looking at the screen shot from @miwojc i don’t see “NSFW” written there. IIRC doesn’t it mention “NSFW” in the result or am i imagining this :rofl:

1 Like

Getting rickrolled : a feature, not a bug.

4 Likes