ST-MFNet is my goto open source: https://
replicate.com/zsxkib/st-mfnet But I also use Topaz AI
@fofrai
-
ST-MFNet and Topaz Video AI for Video Enhancement
By
–
-
Memory Optimization Challenges in AI Systems
By
–
It uses a lot of memory. I don't know, if it doesn't straight away, I expect community optimisations will get it there.
-
Stability AI Video Sampling Script Installation Guide
By
–
Just the vanilla: `python scripts/sampling/simple_video_sample.py` From the repo. Follow the README instructions: https://
github.com/Stability-AI/g
enerative-models#installation
… -
Stability AI Extensions Coming Soon for Comfy and A1111
By
–
Comfy and A1111 extensions will probably come soon.
I'm sunning the Stability AI repo and example python scripts on a GPU. I'm sure @camenduru is already working on a colab. -
AI Video Generation Achieves Realistic Video Game Footage Quality
By
–
Upscaled to 1080p and interpolated to 24fps, and this AI generation looks like actual video game footage (albeit with time paused).
— fofr (@fofrAI) 21 novembre 2023
🤯 https://t.co/XDb2eJiCha pic.twitter.com/ILgd33RgiDUpscaled to 1080p and interpolated to 24fps, and this AI generation looks like actual video game footage (albeit with time paused).
-
Stable Diffusion Video Model Impresses Users with New Capabilities
By
–
Dang! I love this Stable Diffusion Video model 😻 pic.twitter.com/YzMMZ3uqZI
— fofr (@fofrAI) 21 novembre 2023Dang! I love this Stable Diffusion model
-
Stable Diffusion Video experiments with varied seeds
By
–
Some more experiments with Stable Diffusion Video and a Midjourney init image.
— fofr (@fofrAI) 21 novembre 2023
This time the same image prompt was run 10 times but with different seeds.
There's a variety of camera movements, the rain falls and the subject remained coherent (only the last one shows morphing).… https://t.co/XDb2eJi4rC pic.twitter.com/PrTfQzwauWSome more experiments with Stable Diffusion and a Midjourney init image. This time the same image prompt was run 10 times but with different seeds. There's a variety of camera movements, the rain falls and the subject remained coherent (only the last one shows morphing).
-
Special Effects LoRAs: Advancing Creative AI Applications
By
–
I love the idea of special effects loras.
-
Quality degradation in AI models above 25 parameters
By
–
Oh nice! I was going to run some experiments – I assume the quality gradually drops off above 25? How does it tend to degrade?
-
SVD-XT 25 Frames Benchmark on A40 GPU
By
–
Here's the longer SVD-XT 25 frames version.
— fofr (@fofrAI) 21 novembre 2023
This took 159s to run on an A40. pic.twitter.com/7PjACUcsiCHere's the longer SVD-XT 25 frames version.
This took 159s to run on an A40.