JaehaerysNL/StableDiffusion
1
0
Fork 0
mirror of https://github.com/Stability-AI/stablediffusion.git synced 2024-12-22 07:34:58 +00:00
Code Issues Projects Releases Packages Wiki Activity

Update modelcard.md

Browse source
This commit is contained in:
hardmaru 2023-03-25 11:21:41 +09:00 committed by GitHub
parent b69cba5d1a
commit 616d52d267
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
modelcard.md
View file

@ -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. - `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`. - `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](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). **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. 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.