@fofrai - AI Dynamics - Page 55 of 80

i2vgen-xl video generation model speeds up significantly

By

–

05 January 2024 11h39

i2vgen-xl is now running faster – @chenxi_jw has done some great work to speed it up. Steps are now also exposed.

16 frame gen:
50 steps down from ~180s to ~115s
25 steps at ~60s

More steps makes more consistency.https://t.co/CH1PsbwTyK https://t.co/Dgl6FfdYmU pic.twitter.com/ZgAP1Yhj10
— fofr (@fofrAI) 5 janvier 2024

i2vgen-xl is now running faster – @chenxi_jw has done some great work to speed it up. Steps are now also exposed. 16 frame gen:
50 steps down from ~180s to ~115s
25 steps at ~60s More steps makes more consistency. https://
replicate.com/cjwbw/i2vgen-xl

→ View original post on X — @fofrai

5 January 2024

Model Optimization: Fixed 8fps Frame Rate Control Strategy

By

@fofrai

–

04 January 2024 18h19

Aye, there’s no fps control at the moment, it’s fixed to 8fps, but you can choose how many frames to generate. I think there’s also lots of room for optimisation of this model to get it faster.

→ View original post on X — @fofrai

4 January 2024

Single Generation Produces 80-Frame 1280x Video with Remarkable Consistency

By

@fofrai

–

04 January 2024 15h44

Dang!

80 frames
a single generation
10 second video at 1280x

Remarkable consistency here over the time frame (10 minutes to generate though) https://t.co/Dgl6FfdYmU pic.twitter.com/NDm8rqeWee
— fofr (@fofrAI) 4 janvier 2024

Dang! 80 frames
a single generation
10 second video at 1280x Remarkable consistency here over the time frame (10 minutes to generate though)

→ View original post on X — @fofrai

4 January 2024

i2vgen Model Experiment: Character Movement Consistency Across Prompts

By

@fofrai

–

04 January 2024 15h38

An experiment with i2vgen model – I keep the seed and params the same but vary prompt by tweaking action (standing, dancing, crying, etc)

Some pretty solid character movement, consistency is pretty good, only the occasional scary distortion.

12 variations. https://t.co/Dgl6FfdYmU pic.twitter.com/rqTeLC8jt9
— fofr (@fofrAI) 4 janvier 2024

An experiment with i2vgen model – I keep the seed and params the same but vary prompt by tweaking action (standing, dancing, crying, etc) Some pretty solid character movement, consistency is pretty good, only the occasional scary distortion. 12 variations.

→ View original post on X — @fofrai

4 January 2024

i2vgen-xl Image-to-Video Model Now Available on Replicate

By

@fofrai

–

04 January 2024 13h02

Image to video model "i2vgen-xl" is now on Replicate – make 16:9 videos at 1280×704 resolution:https://t.co/CH1PsbwlJc

Example (which I also interpolated):https://t.co/2Rm3lZxaeI

It also seems to work well up to 48 frames. pic.twitter.com/qbowIuCQG2
— fofr (@fofrAI) 4 janvier 2024

Image to video model "i2vgen-xl" is now on Replicate – make 16:9 videos at 1280×704 resolution: https://
replicate.com/cjwbw/i2vgen-xl Example (which I also interpolated): https://
replicate.com/p/lvd42ldbrjr6
mkfje2wawohaja
… It also seems to work well up to 48 frames.

→ View original post on X — @fofrai

4 January 2024

Midjourney to Magnific AI to Topaz Photo AI workflow

By

@fofrai

–

04 January 2024 1h11

Midjourney v6 to Magnific AI 4K
to Topaz Photo AI

→ View original post on X — @fofrai

4 January 2024

AI Predictions for 2023: A Retrospective Comparison Analysis

By

@fofrai

–

02 January 2024 20h56

How do the AI predictions for 2023 compare now?

→ View original post on X — @fofrai

2 January 2024

Artificial Species as Invasive: Ecosystem Destabilization Risks

By

@fofrai

–

02 January 2024 9h31

An invented species would always be an invasive one, wherever you put it. Meaning it risks upsetting any existing ecosystem. Risks are destabilisation of ecosystem, extinction and so on.

→ View original post on X — @fofrai

2 January 2024