Yesterday, I photographed this Organ-pipe lichen (Cladonia crispata) growing between Bristly and Juniper Haircap mosses.
My employer, Shopify, announced layoffs today and I've been affected. If you're looking for someone with deep experience with developer tooling and developer environments, I'd love to work with you. I've spent the last two years building Shopify's in-house cloud developer environment, and I have extensive experience building developer tools as one of members of the Homebrew package manager's Project Leadership Committee.
Layoffs have been hitting some folks I know pretty hard, either directly, or through having to add others' responsibilities on to their own.
My company is hiring for a half dozen positions. One of the positions (Sr Systems Engineer) is on my team. Each of them is a real position that we're actually interviewing to fill.
Domaintools is a great company, filled with some of the smartest and best people I've ever had the pleasure of working with. I've been with FSI and DT (FSI was bought about a year and a half ago by DT) for a total of over 9 years now, and I'm still hyped about my job, the learning opportunities, the people, and the impact we make on the world.
If the layoffs impacted you, and there's a fit, come work with me. If you're unhappy with your position, but the move still sounds like a good idea, come work with me and open your spot for someone else!
Reach out to me with any questions, or if you'd like to ask me to officially recommend you for the position to the hiring manager.
The international #conference on #MachineLearning ( #icml2023 ) has 30 associated workshops, and all of them are calling for contributions right now.
Decided to give DeepFloyd a try today on macOS.
The good news? It works … kinda 😛
The bad news? It doesn’t work all the way … as was to be expected 🙂
I took the following code from their GitHub repo (https://github.com/deep-floyd/IF) and modified for an Apple Silicon (M1) Mac. Here’s the actual code I ran:
from diffusers import DiffusionPipeline
from diffusers.utils import pt_to_pil
import torch
# stage 1
stage_1 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-I-M-v1.0").to("mps")
# stage 2
stage_2 = DiffusionPipeline.from_pretrained("DeepFloyd/IF-II-M-v1.0", text_encoder=None).to("mps")
# stage 3
safety_modules = {"feature_extractor": stage_1.feature_extractor, "safety_checker": stage_1.safety_checker, "watermarker": stage_1.watermarker}
stage_3 = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-x4-upscaler", **safety_modules).to("mps")
prompt = 'a photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the eiffel tower holding a sign that says "very deep learning"'
# text embeds
prompt_embeds, negative_embeds = stage_1.encode_prompt(prompt)
generator = torch.manual_seed(0)
# stage 1
image = stage_1(prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, generator=generator, output_type="pt").images
pt_to_pil(image)[0].save("./if_stage_I.png")
# stage 2
image = stage_2(image=image, prompt_embeds=prompt_embeds, negative_prompt_embeds=negative_embeds, generator=generator, output_type="pt").images
pt_to_pil(image)[0].save("./if_stage_II.png")
# stage 3
image = stage_3(prompt=prompt, image=image, generator=generator, noise_level=100).images
image[0].save("./if_stage_III.png")
You have to make sure that diffusers, transformers, and accelereate (at least in my own trial) are fully up-to-date. The larger models probably work too but it took too long to download/test and so I opted for the smallest models.
Stage I and II generated images but stage III errored out. I will need to figure out what happened there later …
Resulting images are attached …
#DeepLearning #MachineLearning #DeepFloyd #ImageGeneration
Been gone for a while... here is one from my archives.
The sky in Oklahoma is a constant source of inspiration!
Get a print and take it home with you!
https://shelli-fitzpatrick.pixels.com/featured/oklahoma-sunrise-sky-on-fire-shelli-fitzpatrick.html
#sunrise #art #MastoArt #DigitalArt #AYearForArt #artist #ArtPrints #sky #oklahoma #FediArt #FediGiftShop
Purple grapes on the vine, seen on a hillside vineyard in Tuscany.
ART - https://deborah-league.pixels.com/featured/purple-grapes-on-the-vine-deborah-league.html
#mastodon #AYearForArt #Art #artist #MastoArt #buyintoart #digitalart #painting #food #photography #Italy #travel
Just singing away.
#birds #procreate #photography #art #bird #birb
We went to San Francisco Botanical Gardens yesterday, and I took photos of three new birds. These jays were my favorite.