Create
270
4.8k
158
10.4k
Updated: Mar 7, 2025
Download
1 variant available
fp8 SafeTensor
iLL_ULtraReal-FP8.safetensors
8-bit, smaller file (pruned) • 5.75 GB
Verified: a year ago
Download (5.75 GB)
4,7840 1 2 3 4 5 6 7 8 9,0 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
10.4K0 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
(274)
Mar 7, 2025
Illustrious
62.3K0 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
580.5K0 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 9.0 1 2 3 4 5 6 7 8 9K
4.9M0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9M
Felldude
Joined Jun 21, 2023
License:
👍
250 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
❤️
170 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
00 1 2 3 4 5 6 7 8 9
This mixed precision model handled SFW and NSFW prompts extremely well in testing.
Only 6GB
Can be used with the FP32 CLIP commands for added precision.
FP8 UNET had minimal losses and a had additional training to amplify detail at lower precision
This model is under 6Gb but packs a hell of a punch, I had to stop myself from feeding it your prompts as test.