UniPixel Style 🎨 [Experiment]
--[Usable on TensorArt]--
this a sub experiment of my other UniPixel LoRA trained on Wan2.2 T2V model, using a subset of image from the original treated dataset and some added pixelart videos edited to fit 16fps.
Usage Tips (mini ver) :
something to note about Wan2.2 gens, the high noise pass adds motion but will a lot of noise the Low noise pass refine the result focusing on treating the details so:
use both the High and Low for video generation (Low:1.0 , High:0.8)
use the Low only version for image generation
Observations:
most gens looks too vibrant like like they're out of retro kids game
it doesn't handle fast movement well
Description
FAQ
Comments (8)
This looks great, thank you!
Looks really good! Would an i2v variant be possible?
its highly unlikely as training for wan2.2 can be costly.
fucking cool. Gotta test if it enhances I2V
Imagine if we could use this in the future to generate games.
hehe I totally see that, lets hope its something we can run on home computers xD
Please I2V version would be the best!
Great Work man
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.