Key moments:
1:15 Download the Models
1:35 Set Up Google Drive
3:42 Set Up the Nvidia Gpu
4:37 Connect to Google Drive
6:03 Animation Modes
6:37 Interpolation
11:10 Animation Prompts
15:13 Create Video from Frames
In this Deep Learning Tutorial, We’ll take a look at How To Generate AI Images and Art with Stable Diffusion in google colab. First of all, we will take a look at how to set up the notebook and the settings. Then we will see some examples of AI-generated images from text prompts and create a frame interpolation video.
⭐Enroll in OpenCV GPU Course: https://nicolai-nielsen-s-school.teachable.com/p/opencv-gpu-course
⭐Enroll in YOLOv7 Course:https://nicolai-nielsen-s-school.teachable.com/p/yolov7-custom-object-detection-with-deployment
Colab Notebook: https://colab.research.google.com/github/deforum/stable-diffusion/blob/main/Deforum_Stable_Diffusion.ipynb
Patreon: https://www.patreon.com/thecodinglibrary/membership
Join as a member or Patreon to get access to exclusive perks:
https://www.youtube.com/channel/UCpABUkWm8xMt5XmGcFb3EFg/join
GitHub: https://github.com/niconielsen32
Join the public Discord chat here: https://discord.gg/5TBkPHHZA5
We will go more in-depth with some of the mentioned elements in future videos. I’ll be doing other tutorials alongside this one, where we are going to use C++ for Algorithms and Data Structures and Artificial Intelligence. The purpose of this tutorial and channel is to build an online coding library where different programming languages and computer science topics are stored in the YouTube cloud in one place.
Feel free to comment if you have any questions about the things I’m going over in the video or just in general, and remember to subscribe to the channel to help me grow and make more videos in the future. 🙂
Tags for the video:
#StableDiffusion #PretrainedModels #DeepLearning
⭐Enroll in OpenCV GPU Course: https://nicolai-nielsen-s-school.teachable.com/p/opencv-gpu-course
Sa.
I followed all the steps exactly but there seem to be some errors in the code in "Run". Can you help? It stops after 0s and displays the following at the bottom of the Run section:
—————————————————————————
NameError Traceback (most recent call last)
<ipython-input-54-cb30409e1f82> in <module>
480 # dispatch to appropriate renderer
481 if anim_args.animation_mode == '2D' or anim_args.animation_mode == '3D':
–> 482 render_animation(args, anim_args)
483 elif anim_args.animation_mode == 'Video Input':
484 render_input_video(args, anim_args)
1 frames
<ipython-input-45-b7a5e2b7dd7f> in generate(args, return_latent, return_sample, return_c)
296 os.makedirs(args.outdir, exist_ok=True)
297
–> 298 sampler = PLMSSampler(model) if args.sampler == 'plms' else DDIMSampler(model)
299 model_wrap = CompVisDenoiser(model)
300 batch_size = args.n_samples
NameError: name 'model' is not defined
It also highlights this line of code underlined in red
# sample the diffusion model
sample, image = generate(args, return_latent=False, return_sample=True)
Bless you for this, you explained the whole process so well. I am running Stable Diffusion locally with Webui but have been wanting to play with deforum+SD so bad.
hmm no link in description
Hey, thanks a lot for this tutorial.
I'm getting this error every time I try to Create video from frames…
————————-
/content/drive/MyDrive/AI/StableDiffusion/2022-09/20220903000939_%05d.png -> /content/drive/MyDrive/AI/StableDiffu'/content/drive/MyDrive/AI/StableDiffusion/2022-09/sion/2022-09/20220903000939.mp4
—————————————————————————
ValueError Traceback (most recent call last)
<ipython-input-13-3c866f80e278> in <module>
24 fname = f"{path_name_modifier}_%05d.png"
25 all_step_dirs = [os.path.join(args.outdir, d) for d in os.listdir(args.outdir) if os.path.isdir(os.path.join(args.outdir,d))]
—> 26 newest_dir = max(all_step_dirs, key=os.path.getmtime)
27 image_path = os.path.join(newest_dir, fname)
28 print(f"Reading images from {image_path}")
ValueError: max() arg is an empty sequence
—————————————————————————–
What I'm missing?
Thanks for explaining it really well! I've been putting off learning soft soft cuz it looks so intimidating but now that I easily understood the
all workеd
tNice tutorials, good luck- you'll go far
I'd love to collaborate with AI animators for film
Im running the "create video from frames" section and it shows a check, but no video is output
OMG ITS WORKED. Guys it really worked. Thank you
Please, how to fix: ValueError: max() arg is an empty sequence
Sorry to bother. I'm getting this error:
ValueError Traceback (most recent call last)
<ipython-input-9-454b1046edd9> in <module>
24 fname = f"{path_name_modifier}_%05d.png"
25 all_step_dirs = [os.path.join(args.outdir, d) for d in os.listdir(args.outdir) if os.path.isdir(os.path.join(args.outdir,d))]
—> 26 newest_dir = max(all_step_dirs, key=os.path.getmtime)
27 image_path = os.path.join(newest_dir, fname)
28 print(f"Reading images from {image_path}")
ValueError: max() arg is an empty sequence
cana you help me?
love the in depth explanation! Had trouble with a different tutorial skipping over all the setup with the google drive.
why do you have to end every sentence like THIS…
Smart video. Slow down and speak a little more pronounced for clarity please. you can speak well and coherently but you are mumbling a little bro. i can see you making good tutorials. subbed and liked.