Mirrors
/
waifu-diffusion
mirror of https://github.com/harubaru/waifu-diffusion.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

update readme

This commit is contained in:
Patrick Esser 2022-08-16 23:13:39 +02:00
parent b57c05232a
commit d39f5b51a8
1 changed files with 25 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
README.md
View File

@ -78,6 +78,9 @@ steps show the relative improvements of the checkpoints:
Stable Diffusion is a latent diffusion model conditioned on the (non-pooled) text embeddings of a CLIP ViT-L/14 text encoder. Stable Diffusion is a latent diffusion model conditioned on the (non-pooled) text embeddings of a CLIP ViT-L/14 text encoder.
#### Sampling Script
After [obtaining the weights](#weights), link them After [obtaining the weights](#weights), link them
``` ```
mkdir -p models/ldm/stable-diffusion-v1/ mkdir -p models/ldm/stable-diffusion-v1/
@ -88,24 +91,6 @@ and sample with
python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms
``` ```
Another way to download and sample Stable Diffusion is by using the [diffusers library](https://github.com/huggingface/diffusers/tree/main#new--stable-diffusion-is-now-fully-compatible-with-diffusers)
```py
# make sure you're logged in with `huggingface-cli login`
from torch import autocast
from diffusers import StableDiffusionPipeline, LMSDiscreteScheduler
pipe = StableDiffusionPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-3-diffusers",
use_auth_token=True
)
prompt = "a photo of an astronaut riding a horse on mars"
with autocast("cuda"):
image = pipe(prompt)["sample"][0]
image.save("astronaut_rides_horse.png")
```
By default, this uses a guidance scale of `--scale 7.5`, [Katherine Crowson's implementation](https://github.com/CompVis/latent-diffusion/pull/51) of the [PLMS](https://arxiv.org/abs/2202.09778) sampler, By default, this uses a guidance scale of `--scale 7.5`, [Katherine Crowson's implementation](https://github.com/CompVis/latent-diffusion/pull/51) of the [PLMS](https://arxiv.org/abs/2202.09778) sampler,
and renders images of size 512x512 (which it was trained on) in 50 steps. All supported arguments are listed below (type `python scripts/txt2img.py --help`). and renders images of size 512x512 (which it was trained on) in 50 steps. All supported arguments are listed below (type `python scripts/txt2img.py --help`).
@ -149,6 +134,28 @@ non-EMA to EMA weights. If you want to examine the effect of EMA vs no EMA, we p
which contain both types of weights. For these, `use_ema=False` will load and use the non-EMA weights. which contain both types of weights. For these, `use_ema=False` will load and use the non-EMA weights.
#### Diffusers Integration
Another way to download and sample Stable Diffusion is by using the [diffusers library](https://github.com/huggingface/diffusers/tree/main#new--stable-diffusion-is-now-fully-compatible-with-diffusers)
```py
# make sure you're logged in with `huggingface-cli login`
from torch import autocast
from diffusers import StableDiffusionPipeline, LMSDiscreteScheduler
pipe = StableDiffusionPipeline.from_pretrained(
"CompVis/stable-diffusion-v1-3-diffusers",
use_auth_token=True
)
prompt = "a photo of an astronaut riding a horse on mars"
with autocast("cuda"):
image = pipe(prompt)["sample"][0]
image.save("astronaut_rides_horse.png")
```
### Image Modification with Stable Diffusion ### Image Modification with Stable Diffusion
By using a diffusion-denoising mechanism as first proposed by [SDEdit](https://arxiv.org/abs/2108.01073), the model can be used for different By using a diffusion-denoising mechanism as first proposed by [SDEdit](https://arxiv.org/abs/2108.01073), the model can be used for different