Sup!? (Bitcoin-based social media) by Ciro Santilli 35 Updated +Created
Video 1.
Sup!? Buying, Listing and Offers by EMBII
. Source.
Chrome Android extension by Ciro Santilli 35 Updated +Created
Lol it is note possible what a joke. Notably this makes it harder to have of a superior third party password manager like Proton Pass (though there seems to be an autocomplete app as an alternative path), and an ad blocker. Fuck Google.
Also, Chromium is not available on Google Play by default, you can install the apk, but you will miss updates:
Software developed by Nvidia by Ciro Santilli 35 Updated +Created
RDF language by Ciro Santilli 35 Updated +Created
Richard Bates (Silk Road advisor and Ross' friend) by Ciro Santilli 35 Updated +Created
youtu.be/HBTYVVUBAGs?t=178 claims to contain a photo of him without source. He has no easy to find online profiles.
Variety Jones: IRL, is there anyone with a clue at all? A girlfriend, boyfriend, buddy you talk to, etc?
myself: Unfortunately yes, there are two but they think I sold the site and got out, and they're quite convinced of it.
His email was published: baronsyntax@gmail.com. They actaully talked on Google Chat. OMG.
Gavin Andresen by Ciro Santilli 35 Updated +Created
Google Passwords by Ciro Santilli 35 Updated +Created
When they disabled this from Chromium, it was one of the things that prompted Ciro Santilli to switch to Proton Pass.
AMD GPU driver by Ciro Santilli 35 Updated +Created
RDNA by Ciro Santilli 35 Updated +Created
Amazon Elastic Compute Cloud by Ciro Santilli 35 Updated +Created
Erwin Coumans by Ciro Santilli 35 Updated +Created
runwayml/stable-diffusion by Ciro Santilli 35 Updated +Created
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.
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.
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
This took about 2 minutes and generated 6 images under 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:
https://raw.githubusercontent.com/cirosantilli/media/master/Runwayml_stable-diffusion_a-photograph-of-an-astronaut-riding-a-horse.png
TODO how to change the number of images?
A quick attempt at removing their useless safety features (watermark and NSFW text filter) is:
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
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.
City of Light: The Story of Fiber Optics by Ciro Santilli 35 Updated +Created
The book is a bit slow until Charles K. Kao comes along, then it gets exciting.
Virtuoso Universal Server by Ciro Santilli 35 Updated +Created
Ubuntu 18.04 by Ciro Santilli 35 Updated +Created

Unlisted articles are being shown, click here to show only listed articles.