Verified: a day ago
SafeTensor
Type | |
Stats | 60 0 |
Reviews | (7) |
Published | Sep 15, 2024 |
Base Model | |
Training | Steps: 12,000 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Hash | AutoV2 F1F5D8B3C0 |
Example images are made with a variety of checkpoints and prompts. Nothing unusual.
No trigger word
Model only (no text/CLiP)
Adjust strength to your own taste and what's in your chain
Will work better with some checkpoints than others
Hi-Res tends to revert the characteristics of LoRA on upscale
Let me know if you know how to improve performance with hi-res! Do I need to train in layers or mid layer?
Recommend checkpoints
Photorealistic checkpoints
Juggernaut | Analog Madness | Photon | EpicRealism | CineDiffusion
Changelog
v9.0 Entire workflow change. Still improving on it.
v8.0 Upped the strength a lot
v7.0 Refinement: details and generalization
v6.0 Improvement so big I deleted the old versions.