@fofrai

–

22 November 2023 0h02

Dang! I love this Stable Diffusion Video model 😻 pic.twitter.com/YzMMZ3uqZI
— fofr (@fofrAI) 21 novembre 2023

Dang! I love this Stable Diffusion model

22 November 2023

Stable Diffusion Video experiments with varied seeds

By

–

21 November 2023 23h52

Some more experiments with Stable Diffusion Video 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).… https://t.co/XDb2eJi4rC pic.twitter.com/PrTfQzwauW
— fofr (@fofrAI) 21 novembre 2023

Some 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

–

21 November 2023 23h38

I love the idea of special effects loras.

Quality degradation in AI models above 25 parameters

By

–

21 November 2023 23h16

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

–

21 November 2023 23h11

Here's the longer SVD-XT 25 frames version.
This took 159s to run on an A40. pic.twitter.com/7PjACUcsiC
— fofr (@fofrAI) 21 novembre 2023

Here's the longer SVD-XT 25 frames version.
This took 159s to run on an A40.

Text prompt options not yet available in AI tool

By

–

21 November 2023 23h08

I don't think there's a text prompt option with this yet.

63 seconds generation time on A40 GPU

By

–

21 November 2023 23h06

Oh and this took 63s to generate on an A40.

Stable Video Diffusion Text-to-Video Render Performance Analysis

By

–

21 November 2023 23h04

First text-to-video render of Stable Video Diffusion (SVD) from a Midjourney input image.

I'm impressed with

– coherent movement
– video quality
– accuracy with original image

Shame the explosions didn't, uh, explode. pic.twitter.com/qDnZAg0hzF
— fofr (@fofrAI) 21 novembre 2023

First text-to-video render of Stable Diffusion (SVD) from a Midjourney input image. I'm impressed with – coherent movement
– video quality
– accuracy with original image Shame the explosions didn't, uh, explode.

SEINE and Stable Video Diffusion: Advanced AI Video Generation

By

–

21 November 2023 21h32

Yep, SEINE and Stable Diffusion

Stable Video Diffusion Models Released on Hugging Face

By

–

21 November 2023 20h31

Stable Video Diffusion models now on HF.

2 models making videos at 576×1024

– 14 frames
– 25 frameshttps://t.co/VJZtz63rzW

Better than Pika and Gen2? https://t.co/BLAZ61xTia
— fofr (@fofrAI) 21 novembre 2023

Stable Diffusion models now on HF. 2 models making videos at 576×1024 – 14 frames
– 25 frames https://
huggingface.co/stabilityai/st
able-video-diffusion-img2vid-xt
… Better than Pika and Gen2?