Tootfinder

Opt-in global Mastodon full text search. Join the index!

No exact results. Similar results found.
@timbray@cosocial.ca
2025-10-23 17:48:47

Software people will laugh while scrolling this. They won’t admit it’s to keep them from crying: immich.app/cursed-knowledge

Cursed Knowledge | Immich
Cursed knowledge we have learned as a result of building Immich that we wish we never knew.

@heiseonline@social.heise.de
2025-09-23 12:08:00

M.2-Adapter quetscht Mini-SSD ins offizielle Raspi-5-Gehäuse
Der M.2 HAT Compact für den Raspberry Pi nimmt 30 mm kleine SSDs huckepack. Das Ganze passt neben den offiziellen CPU-Kühler.

M.2-Adapter quetscht Mini-SSD ins offizielle Raspi-5-Gehäuse
Der M.2 HAT+ Compact für den Raspberry Pi nimmt 30 mm kleine SSDs huckepack. Das Ganze passt neben den offiziellen CPU-Kühler.

@UP8@mastodon.social
2025-10-22 18:41:27

⚡ What Tax Credit? Hyundai Slashes Ioniq 5 EV Price by Nearly $10,000
thedrive.com/news/what-tax-cre

What Tax Credit? Hyundai Slashes Ioniq 5 EV Price by Nearly $10,000
Ioniq 5 sales surged as buyers looked to take advantage of the now-dead tax credit. This is Hyundai's way of extending that rally.

@arXiv_csCV_bot@mastoxiv.page
2025-09-23 13:11:41

ComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation
Guocheng Gordon Qian, Daniil Ostashev, Egor Nemchinov, Avihay Assouline, Sergey Tulyakov, Kuan-Chieh Jackson Wang, Kfir Aberman
arxiv.org/abs/2509.18092

ComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation
Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a reference image, they lack modularity and fail to provide disentangled control over specific visual attributes. We introduce a new paradigm for attribute-specific image prompting, in which distinct sets of reference images are used to guide the generation of …

@ErikJonker@mastodon.social
2025-08-19 10:50:45

Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency
qwenlm.github.io/blog/qwen-ima

Qwen-Image-Edit: Image Editing with Higher Quality and Efficiency
QWEN CHAT GITHUB HUGGING FACE MODELSCOPE DISCORD We are excited to introduce Qwen-Image-Edit, the image editing version of Qwen-Image. Built upon our 20B Qwen-Image model, Qwen-Image-Edit successfully extends Qwen-Image’s unique text rendering capabilities to image editing tasks, enabling precise text editing. Furthermore, Qwen-Image-Edit simultaneously feeds the input image into Qwen2.5-VL (for visual semantic control) and the VAE Encoder (for visual appearance control), achieving capabiliti…

@muz4now@mastodon.world
2025-08-23 14:22:01

Bandsintown inks YouTube deal to become platform’s exclusive provider of concert listings
#MusicianTips
musicbusinessworld…

Bandsintown inks YouTube deal to become platform’s exclusive provider of concert listings
Integration will soon expand to YouTube’s homepage – and to YouTube Music later this year…

@heiseonline@social.heise.de
2025-10-23 13:14:00

"The Outer Worlds 2" angespielt: Ein vertrauter Aufbruch ins Unbekannte
Obsidian setzt bei "The Outer Worlds 2" den Hebel an den richtigen Stellen an. Selten war eine Fortsetzung dem Original so nah und dennoch so viel besser.

"The Outer Worlds 2" angespielt: Ein vertrauter Aufbruch ins Unbekannte
Obsidian setzt bei "The Outer Worlds 2" den Hebel an den richtigen Stellen an. Selten war eine Fortsetzung dem Original so nah und dennoch so viel besser.

@joxean@mastodon.social
2025-10-23 09:16:20

Scientists Discover Building Blocks of Life in Ice Around a Forming Star (ST6) in Neighboring Galaxy (Large Magellanic Cloud).
cmns.umd.edu/news-events/news/

Using JWST's MIRI, researchers detected complex organic molecules around a young star called ST6 in the LMC. The full galaxy is shown in the far-infrared image (upper right). The main image is a zoom-in on the star-forming region of the LMC. JWST's MIRI image at a wavelength of 19 microns depicts ST6 (bottom right). Credit: NASA/ESA/CSA/JPL-Caltech/M. Sewiło et al. (2025)
A diagram depicting the COMs (complex organic molecules) detected on icy dust grains around ST6: acetaldehyde, acetic acid, ethanol and methyl formate. Credit: NASA's Goddard Space Flight Center.
The infrared spectrum of the protostar ST6 taken by Webb's Mid-Infrared Instrument covering a range of wavelengths where spectral signatures of large complex organic molecules have been found. Credit: NASA's Goddard Space Flight Center/M. Sewilo et al. (2025)
@hllizi@hespere.de
2025-09-23 07:23:23

If I understand that correctly, a container image is built from a base image by creating a container from the base image and then carrying out operations that build up successive layers in an overlay filesystem and then committing the result.
An overlay filesystem is at the core a sequence of directories that is traversed when looking for a file. The first directory that has the file wins, where deletions are just files with a special bit set.
Now to what I am wondering about:

@arXiv_csCV_bot@mastoxiv.page
2025-09-23 13:12:01

Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
Chaehyun Kim, Heeseong Shin, Eunbeen Hong, Heeji Yoon, Anurag Arnab, Paul Hongsuck Seo, Sunghwan Hong, Seungryong Kim
arxiv.org/abs/2509.18096

Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
Text-to-image diffusion models excel at translating language prompts into photorealistic images by implicitly grounding textual concepts through their cross-modal attention mechanisms. Recent multi-modal diffusion transformers extend this by introducing joint self-attention over concatenated image and text tokens, enabling richer and more scalable cross-modal alignment. However, a detailed understanding of how and where these attention maps contribute to image generation remains limited. In thi…