diffusion-models-class
Our great sponsors
diffusion-models-class | deforum-stable-diffusion | |
---|---|---|
22 | 14 | |
3,221 | 2,130 | |
5.5% | 2.5% | |
6.3 | 7.4 | |
19 days ago | about 2 months ago | |
Jupyter Notebook | Python | |
Apache License 2.0 | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
diffusion-models-class
- diffusion low level question
- Here's a learning resource
-
[R] Classifier-Free Guidance can be applied to LLMs too. It generally gives results of a model twice the size you apply it to. New SotA on LAMBADA with LLaMA-7B over PaLM-540B and plenty other experimental results.
When you use stable diffusion, you can adjust the classifier free guidance scale to control how much it follows the input prompt. From what I understand(check https://github.com/huggingface/diffusion-models-class/tree/main/unit3), what cfg does is that it generates an unconditional image and an image conditional on the text prompt, and then scale up the difference.
-
Ai Coding roadmap
https://huggingface.co/learn/nlp-course/ https://huggingface.co/docs/transformers (go through the task guide) https://github.com/huggingface/diffusion-models-class http://d2l.ai/ https://www.youtube.com/watch?v=VMj-3S1tku0&list=PLAqhIrjkxbuWI23v9cThsA9GvCAUhRvKZ
-
How does stable diffusion work from a technical perspective?
I couldn't understand the original paper(havent done meth in a long time). This blog post and short course help me to understand.
-
Using SD programatically with APIs
The Diffusion Models Course is another good resource to learn more technical details.
-
I made a generative 3D game and took a walk in the streets of Paris. Playback speed 30x
Next, you need to become familiar with the diffusion model. I recommend this huggingface's course(https://github.com/huggingface/diffusion-models-class) because it is very high quality and you will learn while using diffusers. At first glance, it may not seem directly related to this game, but in my case, knowing what is happening in diffusers helped me in many ways: trial and error, inspiration for ideas, etc. I had no knowledge of pytorch (the deep learning library used for diffusers), so I also took this course (https://www.udacity.com/course/deep-learning-pytorch--ud188) which was in the prerequisites for that huggingface's course. It was also very good.
- Sunt AI Research Scientist, AMA
-
Dreambooth Hackaton: How can we use a text-to-image model to explore the cinematographic appeal of Torres del Paine 🇨🇱?
Hugging Face Dreambooth Hackaton details
-
[N] Personalise Stable Diffusion models in DreamBooth Hackathon
Details: https://github.com/huggingface/diffusion-models-class/blob/main/hackathon/README.md
deforum-stable-diffusion
-
Stable Zero123: Quality 3D Object Generation from Single Images
This looks a fine-tune of the classic zero123 (https://github.com/cvlab-columbia/zero123) I’m excited to check out the quality improvements.
Though 3d model synthesis is one use case, I found the less advertised base reprojection model to be more useful for gamedev at the moment. You can generate a multiview spritesheet from an image, and it’s fast enough for synthesis during a gameplay session. I couldn’t get a good quality/time balance to do the same with the 3d models, and the lack of mesh rigging or animation combined with imperfections in a fully 3d model tends to break the suspension of disbelief compared to what players are used to. I’m this will change as the tech develops and we layer more AI on top (automatic animation synthesis is an active research area).
If you’re interested in this you might also want to check out deforum (https://github.com/deforum-art/deforum-stable-diffusion) which provides even more powerful camera controls on top of stable diffusion designed for full scenes rather than single objects.
-
Smooth Style and Concept Vid2Vid Conversion - The Inner-Reflections Method - Workflow and Tutorial
2/Deforum – Open source and good at developing trippy videos – I have not used this too much (https://github.com/deforum-art/deforum-stable-diffusion)
-
Stability Announces Stable Animation
Why is StabilityAI releasing what seems to be a clone of Deforum ?
- Astral Projection...!
-
How would someone create this AI art video?
might be deforum (project) (webui extension) or img2img loopback wave (webui extension). it's definitely something with img2img though. that's clear from how it's warping.
- Amsterdam trip) Smoking stable diffusion and drinking deforum)
-
First time output video by StableDiffusion
Sorry, I missed it, thanks to Deforum: https://github.com/deforum-art/deforum-stable-diffusion
- Walking in a winter dream
-
Music video remix concept ideas / help needed
Have you seen Deforum? Kinda sounds like you're about to reinvent it. :)
-
Deforum Stable Diffusion Local
I'm talking about it https://github.com/deforum-art/deforum-stable-diffusion It is not possible to put in a separate environment.
What are some alternatives?
UnstableFusion - A Stable Diffusion desktop frontend with inpainting, img2img and more!
stable-diffusion-nvidia-docker - GPU-ready Dockerfile to run Stability.AI stable-diffusion model v2 with a simple web interface. Includes multi-GPUs support.
tutorials - AI-related tutorials. Access any of them for free → https://towardsai.net/editorial
automatic - SD.Next: Advanced Implementation of Stable Diffusion and other Diffusion-based generative image models
approachingalmost - Approaching (Almost) Any Machine Learning Problem
deforum-for-automatic1111-webui - Deforum extension script for AUTOMATIC1111's Stable Diffusion webui [Moved to: https://github.com/deforum-art/sd-webui-deforum]
pml-book - "Probabilistic Machine Learning" - a book series by Kevin Murphy
Stable-diffusion-webui-video-multiprompt - I added multiprompt functionality to this script, so that one can input a path to a file containing the "screenplay".
deforumed-walk - Take a walk in the generated world.
sd-webui-controlnet - WebUI extension for ControlNet
diffusers - 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.