Generating Images with AI - Stable Diffusion updates
Generating Images with AI - Stable Diffusion updates
October 26, 2024
Exactly Two years ago from this moment I was able to generate the following:
How much is 2 years in GenAI?
Well…lets find that out.
Stable Diffusion Models📌
Using APIs to Generate Images from Text
ℹ️
I tested Dalle3 Model via OpenAI API (while dev StreamlitMultichat), at this script
Other Interesting APIs
Get access to multiple AI models for the price of one.
FAQ
Stable Difussion + DreamBooth to make custom Pictures
It was all possible thanks to this DotCSV YT Video
Does it work now?
Foocus
Confy-UI
Flux
https://www.youtube.com/watch?v=r-uH1C_Vi08
Using HuggingFace
Text2Video
So in 2024…it is text to video.
- Mochi-1 - https://www.youtube.com/watch?v=WKyaGpiOjW4
- AI Video generation with HeGyGe
InVideo -
Workflow: go to Elon Munsk Twitter -> ChatGPT to create the speech
- Create thumbnail with Flux (via SeArt.ai), 9/16 format for YT Short
- Then go with the speech to elevenlabs (T2S) - Download Audio
- Use CapCut
ℹ️
With seart you can do Image2Video - I2V
GPUs for AI
- RunPod
- Kutrim