Conda install is a bit annoying, but gets the job done. The generation quality is very good.
Someone should package this better for end user "just works after Conda install" image generation, it is currently much more of a library setup.
Tested on Amazon EC2 on a g5.xlarge machine, which has an Nvidia A10G, using the AWS Deep Learning Base GPU AMI (Ubuntu 20.04) image.
First install Conda as per Section "Install Conda on Ubuntu", and then just follow the instructions from the README, notably the Reference sampling script section.This took about 2 minutes and generated 6 images under
git clone https://github.com/runwayml/stable-diffusion
cd stable-diffusion/
git checkout 08ab4d326c96854026c4eb3454cd3b02109ee982
conda env create -f environment.yaml
conda activate ldm
mkdir -p models/ldm/stable-diffusion-v1/
wget -O models/ldm/stable-diffusion-v1/model.ckpt https://huggingface.co/CompVis/stable-diffusion-v-1-4-original/resolve/main/sd-v1-4.ckpt
python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms
outputs/txt2img-samples/samples
, includining an image outputs/txt2img-samples/grid-0000.png
which is a grid montage containing all the six images in one:TODO how to change the number of images?
A quick attempt at removing their useless safety features (watermark and NSFW text filter) is:but that produced 4 black images and only two unfiltered ones. Also likely the lack of sexual training data makes its porn suck, and not in the good way.
diff --git a/scripts/txt2img.py b/scripts/txt2img.py
index 59c16a1..0b8ef25 100644
--- a/scripts/txt2img.py
+++ b/scripts/txt2img.py
@@ -87,10 +87,10 @@ def load_replacement(x):
def check_safety(x_image):
safety_checker_input = safety_feature_extractor(numpy_to_pil(x_image), return_tensors="pt")
x_checked_image, has_nsfw_concept = safety_checker(images=x_image, clip_input=safety_checker_input.pixel_values)
- assert x_checked_image.shape[0] == len(has_nsfw_concept)
- for i in range(len(has_nsfw_concept)):
- if has_nsfw_concept[i]:
- x_checked_image[i] = load_replacement(x_checked_image[i])
+ #assert x_checked_image.shape[0] == len(has_nsfw_concept)
+ #for i in range(len(has_nsfw_concept)):
+ # if has_nsfw_concept[i]:
+ # x_checked_image[i] = load_replacement(x_checked_image[i])
return x_checked_image, has_nsfw_concept
@@ -314,7 +314,7 @@ def main():
for x_sample in x_checked_image_torch:
x_sample = 255. * rearrange(x_sample.cpu().numpy(), 'c h w -> h w c')
img = Image.fromarray(x_sample.astype(np.uint8))
- img = put_watermark(img, wm_encoder)
+ # img = put_watermark(img, wm_encoder)
img.save(os.path.join(sample_path, f"{base_count:05}.png"))
base_count += 1
Uniqueness results for the composition series of a group.
The cool thing about this notation is that is showed to Ciro Santilli that there is more state to a chess game than just the board itself! Notably:plus some other boring draw rules counters.
- whose move it is next
- castling availability
- en passant availability
Coinbase message are messages that only miners can embed in the blockchain.
As such most of them tend to be boring ads for mining pools, but there are a few exceptions, especially in the early days.
Two Photon Microscopy by Nemonic NeuroNex (2019)
Source. Shows a prototype of a two-photon electron microscope on an optical table, and describes it in good detail, well done.Can you imagine when those guys started to see moons in other planets? They must have shat bricks. What better evidence can you have that the geocentric model could be wrong?
From cocodataset.org/:
- 330K images (>200K labeled)
- 1.5 million object instances
- 80 object categories
- 91 stuff categories
- 5 captions per image. A caption is a short textual description of the image.
So they have relatively few object labels, but their focus seems to be putting a bunch of objects on the same image. E.g. they have 13 cat plus pizza photos. Searching for such weird combinations is kind of fun.
Their official dataset explorer is actually good: cocodataset.org/#explore
And the objects don't just have bounding boxes, but detailed polygons.
Also, images have captions describing the relation between objects:Epic.
a black and white cat standing on a table next to a pizza.
This dataset is kind of cool.
There are unlisted articles, also show them or only show them.