Plutonic Rainbows

wan-i2v

February 25, 2025

Another image-to-video model, this time wan-i2v which claims to be the next evolution in video generation.

Built upon the mainstream diffusion transformer paradigm, Wan2.1 achieves significant advancements in generative capabilities through a series of innovations, including our novel spatio-temporal variational autoencoder (VAE), scalable pre-training strategies, large-scale data construction, and automated evaluation metrics. These contributions collectively enhance the model’s performance and versatility

Open New Page

February 24, 2025

Trying to figure out a way to open links in new tabs.

Veo2

February 24, 2025

Pretty incredible results with this new model. It responds very well to prompting.

Snow falling on a fairground in Vienna.

Generated result is here. The only issue right now is that generation fees have dropped so the queue time is very long.

Topaz Labs claims to have introduced the world’s first and only diffusion-based video enhancement. From my experience with poor-quality 1990s VHS tapes, the results so far have been quite astonishing.

Project Starlight is a groundbreaking AI research preview by Topaz Labs that transforms low-resolution and degraded video into HD quality.

It's the first-ever diffusion AI model for video enhancement and the only one to achieve full temporal consistency, ensuring seamless motion from frame to frame. Users can access the research preview online or in Video AI.

Smart Object

February 23, 2025

Turn layer into Smart Object
Edit in Camera Raw
Click Smart Filter Thumbnail and paint with mask