Download
1 variant available
fp16 SafeTensor
DVAnimated V1.fp16.safetensors
Half precision, best balance (pruned) • 1.99 GB
Verified: 2 years ago
5550 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(63)
Mar 2, 2024


5570 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
1.5K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
16.4K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

Highly stylized cartoon model, base trained and further merged until I liked what I ended up with. This isn't a do-it-all model, it does what it does with plenty of flexibility. It's a starting point for the model that I plan to work on more in the future.
Recommended settings:
CFG: I use 3, I would avoid going too high.. 3-5 seems about right.
Steps: I haven't tested on lower than 30. That's just my default.
HiRez Noise: I use .25, haven't tried higher.
HiRez Steps: 20-30 seems good.
Sampler: I personally use DPM++ 3M SDE Karras but Euler A is solid. I have a couple example images above.
