From b69cba5d1aa57655d1ee3cbabf0d02e1c4535c49 Mon Sep 17 00:00:00 2001 From: hardmaru Date: Sat, 25 Mar 2023 11:20:26 +0900 Subject: [PATCH] Update modelcard.md --- modelcard.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/modelcard.md b/modelcard.md index 3cdfdee..a531218 100644 --- a/modelcard.md +++ b/modelcard.md @@ -97,7 +97,7 @@ We currently provide the following checkpoints, for various versions: - `512-base-ema.ckpt`: Fine-tuned on `512-base-ema.ckpt` 2.0 with 220k extra steps taken, with `punsafe=0.98` on the same dataset. - `768-v-ema.ckpt`: Resumed from `768-v-ema.ckpt` 2.0 with an additional 55k steps on the same dataset (`punsafe=0.1`), and then fine-tuned for another 155k extra steps with `punsafe=0.98`. -**SD-unCLIP 2.1** is a finetuned version of Stable Diffusion 2.1, modified to accept (noisy) CLIP image embedding in addition to the text prompt, and can be used to create image variations ([Examples](../assets/stable-samples/stable-unclip/unclip-variations_noise.png)) or can be chained with text-to-image CLIP priors. The amount of noise added to the image embedding can be specified via the `noise_level` (0 means no noise, 1000 full noise). +**SD-unCLIP 2.1** is a finetuned version of Stable Diffusion 2.1, modified to accept (noisy) CLIP image embedding in addition to the text prompt, and can be used to create image variations ([Examples](https://github.com/Stability-AI/stablediffusion/blob/main/doc/UNCLIP.MD) or can be chained with text-to-image CLIP priors. The amount of noise added to the image embedding can be specified via the `noise_level` (0 means no noise, 1000 full noise). If you plan on building applications on top of the model that the general public may use, you are responsible for adding the guardrails to minimize or prevent misuse of the application, especially for use-cased highlighted in the earlier section, Misuse, Malicious Use, and Out-of-Scope Use.