diffusers-interpret
CogVideo
diffusers-interpret | CogVideo | |
---|---|---|
15 | 39 | |
259 | 3,506 | |
- | 1.2% | |
10.0 | 2.4 | |
over 1 year ago | 11 months ago | |
Jupyter Notebook | Python | |
MIT License | Apache License 2.0 |
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.
diffusers-interpret
- Stable Diffusion links from around September 29, 2022 that I collected for further processing
-
Diffusers-Interpret π€π§¨π΅οΈββοΈ - Model explainability for π€ Diffusers
Check the project at https://github.com/JoaoLages/diffusers-interpret
- Diffusers-Interpret v0.4.0 is out! Explainability for Stable Diffusion
-
Can we please make a general update on all the "most important" news/repos available?
For those who want to explore what the denoising process looks like, check out the [diffusers-interpret package](https://github.com/JoaoLages/diffusers-interpret)! You can generate a GIF like [this one](https://github.com/TomPham97/diffuser/blob/main/diffusion-process.gif?raw=true).
-
Commas, How do they work?!
If you have lots of RAM the diffusers-interpreter is an explainability tool that can show exactly how much each token is beings weighted and which part of the image it is influencing.
-
[D] Senior research scientist at GoogleAI, Negar Rostamzadeh: βCan't believe Stable Diffusion is out there for public use and that's considered as βokβ!!!β
github.com/JoaoLages/diffusers-interpret
- Model explainability for π€ Diffusers. Get explanations for your generated images with the latest stable diffusion model!
- [P] Model explainability for π€ Diffusers. Get explanations for your generated images with the latest stable diffusion model!
CogVideo
-
InstructPix2Pix Video: "Turn the wave into trash"
Additionally two open source demo models [CogVideo[(https://github.com/THUDM/CogVideo) by a groups of cs students a model by [Antonia Antonova](https://antonia.space/text-to-video-generation) and have presented their own innovative methods of generating video from text
-
Effortpost: The Future Of Media Synthesis and AI Art
The second thing that will happen is the appearance of AI video and audio. Google has shown two programs for video generation, one which is fairly high quality and the other which can make long videos with several scenes. Meta has also demonstrated their own. We've already seen other projects like CogVideo, as well as many others that are currently being worked on. It's likely that these techniques will become so refined that over the next year or two, they'll have a similar boom to image generation programs. And eventually, they'll have a similar application in video editing, once coherence is adequate enough. Select a person's shirt, and it stays that for the remainder of the scene. Change an actor's hairstyle in real time, or add characters that didn't exist into a scene and let the computer figure out the desired level of realism. This'll revolutionize VFX to a degree where making an effects heavy will be less about wrangling complex toolsets and more about making aesthetic choices of style and placement.
- AI Content Generation, Part 1: Machine Learning Basics
- Can we please make a general update on all the "most important" news/repos available?
-
Stable Diffusion Public Release β Stability.ai
Check out https://github.com/THUDM/CogVideo - progress is being made on coherent video generation.
Characters and dialogue are effectively solved, just look at GPT-3.
The entity behind StableDiffusion is also supporting generative music art, so let's see what is coming out of that: https://www.harmonai.org/
We are currently far away from generating a production quality movie with AI, but I don't think it's going to be nearly as long as a lifetime. In my opinion, we'll have high quality AI shorts within the decade.
-
How far away are we from have AI like DALL-E 2 be able to create other media like 3d models or video?
CogVideo and a CogView web app.
-
Does training transformers on large corpuses of music files have some hidden difficulty which makes it impossible?
A better comparison to AI music generation would be video generation, which has not improved much since i saw first examples some years ago. The last iteration is stuff like CogVideo and this is only able to generate 4 second videos with mid-strong artifacts.
-
[R] CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers + Gradio Web Demo
github: https://github.com/THUDM/CogVideo
- CogVideo: Code and 94B Model for Text-to-Video Generation via Transformers
-
CogVideo (text-to-video) model, code, and demo are available
GitHub repo.
What are some alternatives?
stable-diffusion-webui - Stable Diffusion web UI
stable-diffusion-ui - Easiest 1-click way to install and use Stable Diffusion on your computer. Provides a browser UI for generating images from text prompts and images. Just enter your text prompt, and see the generated image. [Moved to: https://github.com/easydiffusion/easydiffusion]
diffusionbee-stable-diffusion-ui - Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
dalle-playground - A playground to generate images from any text prompt using Stable Diffusion (past: using DALL-E Mini)
diffusion-ui - Frontend for deeplearning Image generation
stable-diffusion - Optimized Stable Diffusion modified to run on lower GPU VRAM
stable-diffusion-webui-feature-showcase - Feature showcase for stable-diffusion-webui
stable-diffusion - A latent text-to-image diffusion model
stable-diffusion
imagen-pytorch - Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch