Month: February 2024

tamlinweek:

Tamlin Week Coloring Pages 2024

We have a very special surprise for everyone!

If you have been struggling to find a way to participate in Tamlin Week, or if you just want to do some relaxing grown-up coloring, you’re in luck! Four of the Tamlin fandom’s artists have drawn up some never-before-seen coloring pages featuring our favorite High Lord!

Tamlin Playing the Fiddle by @copypastus

Tamlin’s Beast Form by @thrumugnyr

Tamlin’s Mask by @taymartiart

Tamlin’s Masked Portrait by @ladymidnight-goesforth

You can access all of the coloring pages in our Google Drive folder here, where they are in much higher quality than we can post on tumblr. Each page has the option to download with or without the background, depending on your preference. You may publish your colored masterpieces for Tamlin Week (April 14-20), or just enjoy them in private!

While the pictures are free to use, please give credit where credit is due and tag the original artists when you upload your finished work! Please do not alter or re-upload the artists’ original line drawings and/or take credit for their work. Please do share your work and tag @tamlinweek so that we can see it, too!

Coloring Tips:

The images can either be colored traditionally, or digitally using your software of choice. For example, photopea.com is free to use and acts just like Photoshop!

If you choose to go the traditional route, Lady Midnight recommends printing the images on a heavier paper like cardstock. (Neenah Classic Crest in Solar White, 80 lb is her paper of choice for marker work, for example.) Consider using alcohol ink markers, colored pencils like Prismacolor, and/or light washes of watercolor to add color to your project.

Thank you, artists! And happy coloring to you all!

rbillustration:

Digital fantasy illustration of a knight-like figure in armour with a long red cloak, stalking through the hallways of a ruined castle with a greatsword held over one shoulder. He has a broken, golden crown floating over his head, and is looking towards the viewer with one wide, glowing eye. He has brown skin, long dark hair and a blue tunic, with one arm formed of enchanted floating armour connected together with glowing pink magic. Framing the image are the tattered remains of a painting of a woman holding a baby. The same yellow baby blanket is held in the man's hand.ALT
Close-up of the first image in the thread, showing the man's wild-eyed stare into the cameraALT

Centuries after his demise at the hands of his own people, the Forgotten King stalks the hallways he once ruled, riddled by tattered memories of a once-blessed life.

The moment he turns his haunted gaze upon you, it is already too late. Run. 👑⚔

Keep reading

augustdementhe:

cascadiarch:

leafie-draws:

I think the biggest downside to having animal ears and a tail would be trying to mask your discomfort in public like imagine trying to play it cool in customer service but your tail keeps bristling

manager: you’re not wagging enough

Wearing a headband that forces my ears forward and busting a fucking blood vessel.

halcyonhue:

I just want you all to know, that if and when this site does experience a real exodus and/or get sunsetted for good, even if we don’t keep in touch I’ll remember you so fondly. You’re the online equivalent of the other kid on the beach where we built sandcastles together; the girl at the campsite where we explored the trees. You’re the drunk person who shared kind words in the bathroom at the club, you’re the talented artists at the life drawing class or the poetry night in a city where I don’t live anymore. It makes me sad that maybe in the future our paths won’t cross so easily, but even when we leave this little shared piece of cyberspace, carried away on our briefly intersecting trajectories, just know I still love you

tevruden:

Tevruden’s change into his dragon form is never consistent, especially with the wings.

Sometimes it’s current arms into wings, sometimes it’s growing new wings.

falindrith:

sumikatt:

the darling Glaze “anti-ai” watermarking system is a grift that stole code/violated GPL license (that the creator admits to). It uses the same exact technology as Stable Diffusion. It’s not going to protect you from LORAs (smaller models that imitate a certain style, character, or concept)

An invisible watermark is never going to work. “De-glazing” training images is as easy as running it through a denoising upscaler. If someone really wanted to make a LORA of your art, Glaze and Nightshade are not going to stop them.

If you really want to protect your art from being used as positive training data, use a proper, obnoxious watermark, with your username/website, with “do not use” plastered everywhere. Then, at the very least, it’ll be used as a negative training image instead (telling the model “don’t imitate this”).

There is never a guarantee your art hasn’t been scraped and used to train a model. Training sets aren’t commonly public. Once you share your art online, you don’t know every person who has seen it, saved it, or drawn inspiration from it. Similarly, you can’t name every influence and inspiration that has affected your art.

I suggest that anti-AI art people get used to the fact that sharing art means letting go of the fear of being copied. Nothing is truly original. Artists have always copied each other, and now programmers copy artists.

Capitalists, meanwhile, are excited that they can pay less for “less labor”. Automation and technology is an excuse to undermine and cheapen human labor—if you work in the entertainment industry, it’s adapt AI, quicken your workflow, or lose your job because you’re less productive. This is not a new phenomenon.

You should be mad at management. You should unionize and demand that your labor is compensated fairly.

some things in here are good points (larger watermarks, for one). However, it is also full of weird not really true info about the glaze project itself:

“glaze is a grift” – Glaze is an academic research project released for free. Only people being grifted here are grad students (that’s a different post entirely). The paper itself won awards at a peer reviewed conference.

(USENIX Best Papers, https://www.usenix.org/conferences/best-papers, Retrieved on 2/28/24)

“glaze violated gpl/stole code” – True to the letter, however extremely easy to show that this was rapidly resolved by the researchers. 3 days! complete rewrite!

(Release Notes, https://glaze.cs.uchicago.edu/release.html, Retrieved on 2/28/24)

“glaze uses the same tech as stable diffusion” – yes because it was designed as an attack against a class of models called diffusion models, of which, stable diffusion is the most well-known open source implementation. It uses the same encoders to develop image perturbations that interfere with the latent embedding of the image in a way that is honestly pretty cool:

(Shawn Shan et al., “Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models,” in 32nd USENIX Security Symposium (USENIX Security 23) (Anaheim, CA: USENIX Association, 2023), 2187–2204, https://www.usenix.org/conference/usenixsecurity23/presentation/shan, p. 7)

To understand the above, you need to know that diffusion models represent what they’re generating in a “feature space” (numbers). The authors noticed that style transfer could be combated if you knew which numbers in that feature space affected artist style. They then did something pretty clever: they computed what something would look like if you applied a public domain style to it, and then made it so that your input would look like the public domain style in the feature space. This is why there are artifacts in a glazed image; it’s actually changing the image data so it looks different when the machine runs its encoder. The researchers’ choice to then use stable diffusion (it’s cited, [67] in section 5.2 step 2) to run style transfer should then make intuitive sense: if mr. AI then uses the same encoder the researchers did to fine tune his model, then their modified image will clog up his machinery just as shown in the paper.

“de-glazing images is as easy as upscaling it” – no it’s not lmao read the paper. this is directly addressed:

(ibid, p. 13)

The overall point of this not being a perfect defense is actually something I agree with. Glaze is so narrow that it only encompasses fine-tuning (e.g. Dreambooth) so it wasn’t really a global defense to begin with (nightshade does better, but not perfectly, in that regard, read their paper, it’s cool). However, the actual claim that you can “just upscale it” in this post is easily proven false.

As an aside, Glaze can be de-glazed pretty well, but it is not a simple process. There is even a paper and open source code that does this (and it, too, is pretty cool): https://github.com/paperwave/Impress. Just to show that it’s also like a published paper, here’s the citation:

Jinghui Chen Bochuan Cao Changjiang Li, Ting Wang, Jinyuan Jia, Bo Li, “IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI,” in The 37th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, Louisiana, USA., 2023, https://arxiv.org/abs/2310.19248.

way too much effort to put in to this post but like fr cite your got dam sources it’s so easy (and free!) to do.

(and use a big watermark/low quality images when posting online that’s also free and easy)

bluebeetle:

(Edit: *EVER not Never, typo but you can’t edit polls after making them)

What are the most notes you’ve never gotten on an original post you’ve made on Tumblr?

10

100

1,000

5,000

10,000

25,000

50,000

75,000

100,000

250,000

500,000+

I’ve never gotten double digits / show results

Pick the number closest to whatever number you actually got, there’s only 12 options and I didn’t want to clutter this with too many numbers… I may make another one if it ends up really skewed to the lower numbers, but I used my own posts as reference.

aubrietarose:

Might do more with this, might not, mostly just wanted to get the images out of my head.

Have some werewolf scribbles.