blended-latent-diffusion
Kandinsky-2
| blended-latent-diffusion | Kandinsky-2 | |
|---|---|---|
| 1 | 15 | |
| 514 | 2,699 | |
| - | 1.1% | |
| 4.5 | 5.7 | |
| 5 months ago | 11 days ago | |
| Jupyter Notebook | Jupyter Notebook | |
| 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.
blended-latent-diffusion
-
Blended Latent Diffusion's code has been released.
The research paper https://arxiv.org/abs/2206.02779 has finally released their code https://github.com/omriav/blended-latent-diffusion after I asked about it 2 days ago in an issue.
Kandinsky-2
- New Kandinsky 2.2 was released. Now with controlnets and code for lora fine-tuning.
-
List of offline (locally runnable) stable diffusion user interfaces
Kandisnky-2 - This isn't stable diffusion, but it's stable-diffusion-2.1 like in all the ways that people love and don't love. Has a nice UI and some style preset prompts, but the problem for Kandinsky is the same one facing SD2.1 - the quality of its output is only marginally superior to what can be achieved in SD1.5. No one will move on from SD1.5 until the superiority of the results are more appealing than the pain involved in abandoning all the tooling and training that has gone into SD1.5.
- AI to morph multiple images together, does it exist?
- Any free generative AI tool that can combine different images into one?
- 80s dystopian Sci-fi Aesthetic with Kandinsky 2.1 Base Model.
-
Do you think free & open source image generators will get to be as good as Midjourney v5 in the near future?
already
- Kandinsky 2.1: open-source txt2img generator, image blending, beats SD on FID
- replacement for Midjourney remix?
-
We've added Kandinsky v2.1 to our open-source app - You can try it for free!
Kandinsky's repo: https://github.com/ai-forever/Kandinsky-2.git
- Is it possible to use Kandisky 2.0 w/ AUTOMATIC1111?
What are some alternatives?
Diffusion-Models-Papers-Survey-Taxonomy - Diffusion model papers, survey, and taxonomy
ComfyUI - The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.
Rerender_A_Video - [SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation
glami-1m - The largest multilingual image-text classification dataset. It contains fashion products.
stable-diffusion-webui - Stable Diffusion web UI
DiffusionFastForward - DiffusionFastForward: a free course and experimental framework for diffusion-based generative models
awesome-generative-ai - A curated list of Generative AI tools, works, models, and references
MultiDiffusion - Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)
infinite-zoom-stable-diffusion - resources for creating Ininite zoom video using Stable Diffiusion, you can use multiple prompts and it is easy to use.
paper-implementations - Attempts to implement various deep learning, computer vision papers.
Kandinsky-Numworks - A small module allowing to link the kandinsky module, from the Numworks, to a window.