diff options
| author | AUTOMATIC1111 <16777216c@gmail.com> | 2023-03-11 08:45:31 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-03-11 08:45:31 +0000 |
| commit | a11ce2b96cc933ebb9e10d46603a89457ddcb9df (patch) | |
| tree | 4c9efccb08f591e3a27b7dab6e39ce4adab17bab /javascript | |
| parent | 0cc0ee1bcb4c24a8c9715f66cede06601bfc00c8 (diff) | |
| parent | 5fef67f6ee949a61826a3a043ea8610fd89fc371 (diff) | |
| download | stable-diffusion-webui-gfx803-a11ce2b96cc933ebb9e10d46603a89457ddcb9df.tar.gz stable-diffusion-webui-gfx803-a11ce2b96cc933ebb9e10d46603a89457ddcb9df.tar.bz2 stable-diffusion-webui-gfx803-a11ce2b96cc933ebb9e10d46603a89457ddcb9df.zip | |
Merge pull request #7710 from space-nuko/unipc
Implement UniPC sampler
Diffstat (limited to 'javascript')
| -rw-r--r-- | javascript/hints.js | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/javascript/hints.js b/javascript/hints.js index f1199009..7f4101b2 100644 --- a/javascript/hints.js +++ b/javascript/hints.js @@ -6,6 +6,7 @@ titles = { "GFPGAN": "Restore low quality faces using GFPGAN neural network", "Euler a": "Euler Ancestral - very creative, each can get a completely different picture depending on step count, setting steps higher than 30-40 does not help", "DDIM": "Denoising Diffusion Implicit Models - best at inpainting", + "UniPC": "Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models", "DPM adaptive": "Ignores step count - uses a number of steps determined by the CFG and resolution", "Batch count": "How many batches of images to create (has no impact on generation performance or VRAM usage)", |