Strength in numbers...

Comments: 0
Anime  

Call Of The Night 2, episode 9

Ten years ago on Halloween, Our Vengeful Hot Detective’s life fell apart. Now it’s Halloween again, and the game is afoot! Except she’s not really a great runner. Some fan-service by Our Hot Undead Teacher and Our Still-Getting-Bigger Childhood Friend, but we’re rapidly moving into the endgame, so keep your eyes on the plot. Our Appropriately-Dressed Hero seems to be the only one who really cares what Anko/Kyoko’s goal is, but will he figure it out before it’s too late?

Verdict: so we’ve got a pattern now: more conventional storytelling = better animation.

(sadly, nobody dresses up like this for Halloween…)

Kaiju No. 8 2, episode 7

Conflict Builds Character. In this case, it finally establishes that Faux-Hawk Fang-Boy actually has a character, as he realizes that even a prima donna needs backup.

Verdict: someday there will be a shonen anime that does not use the “I must get stronger” trope. This isn’t going to be it. Still well-done, though.

(Magia Sulfer says, “suit up and show up!”)

Wait, “isekai potion loli” is a genre now?!?

Looking at next season, and not finding much of anything to watch. Folks who keep up with My Hero Academia are likely interested in the final season, and folks into Spy x Family have something to look forward to, but that doesn’t help me, unless I were to spend half the season catching up on them first.

Gate manga 22 & 23 out

You know what that means, right? A picture of Rory Mercury:

Dear Microsoft,

You won’t let me turn off the on-by-default sharing of data with third-party advertisers unless I first turn off my ad-blocker? Fucktards.

(note that this isn’t a browser setting, it’s system-wide, and it includes data hoovered up by Copilot, which I was in the process of turning off at the time…)

Why Boys Aren’t Reading

There’s been a bit of a fuss on social media where leftsplainers handwave away pretty much any negative thing about boys, and recently they’re claiming that boys aren’t reading because there’s just nothing being written for boys. At which point dozens of successful authors pile on and point out that publishing has been run by far-left women and female impersonators for so long that most of them had to go indie to be published at all, and that boys exposed to decent books will gobble them like candy.

I was thinking about this in the grocery store last night, because as I was hiking from the sporting goods department to the egg vault (Meijer stores are quite large), I passed a prominent, colorful display that boldly advertised “Reading For Children”.

Every book was for girls. Only.

“Change my mind” 1

The world was a better place when it was possible to buy ammo at the grocery store at 2 AM.

(thanks to looooooong Covid, now I can’t buy much of anything at 2 AM, except at gas-station convenience stores)

“Change my mind” 2

LLMs that show their “reasoning” are simply writing fan-fic in a parallel thread that has nothing to do with the process used to produce the actual output.

(last night’s “generate 200 unique sexy pin-up poses” test produced a list of 34 unique poses repeated an average of ~6 times, despite the extensive “reasoning” process it fabricated; and they weren’t even particularly interesting poses)

Prompts and Vision

Two things I’d never really played with are using LLMs to “improve” prompts, and using specialized LLMs that can analyze a picture and describe the contents.

Prompt enhancement is… hit or miss, but it’s good at turning the usual list-of-keywords prompting into real sentences and paragraphs, which makes a difference with Qwen Image’s LLM parser. I’ll do some before/after pics of that at some point.

Pity that they’re just as censored when “enhancing” as they are when handling other requests. openai-gpt-oss is just as big a nag as their online models, and the attempts people have made to “uncensor” it haven’t been fully successful yet; I’m not asking it to describe a gang-bang, but it still goes full wokescold when you ask for something simple like a list of “Fifties sexy pin-up poses”. Because it’s not respectful, according to some purple-haired pierced gender-ambiguous 23-year-old in San Francisco.

On to vision! For today (since this is a four-day weekend for me…), let’s try something simple: given a real photograph, ask two LLMs to “describe the contents of the image in detail”, then feed the resulting prompt to Qwen Image.

J in Japan:

mistral-small-3.2:

The image captures a serene scene from a Japanese garden, bathed in the soft glow of daylight. Dominating the center of the image is a tranquil pond, its surface disturbed only by the gentle ripples created by two koi fish. The koi, their scales shimmering in hues of orange and white, are swimming near the surface of the water, adding a sense of life and movement to the otherwise still scene.

On the right side of the pond, a stone lantern stands guard. Its weathered surface tells a story of time passed, and it’s partially submerged in the water, as if it has been there for ages. The lantern’s presence adds an element of mystery and intrigue to the scene.

The pond is nestled amidst lush greenery. Various plants and trees surround it, their leaves rustling gently in the breeze. The foliage is a mix of different shades of green, creating a vibrant tapestry that contrasts beautifully with the blue-green waters of the pond.

The overall composition of the image suggests a place of peace and tranquility, where one can escape from the hustle and bustle of daily life. It’s a snapshot of nature’s beauty, captured in all its glory.

qwen2.5-vl-7b:

The image depicts a tranquil garden scene centered around a small pond. The pond is surrounded by lush greenery, including various plants and shrubs that add vibrant colors to the setting. On one side of the pond, there are yellow flowers that stand out against the green backdrop.

In the middle of the pond, two koi fish can be seen swimming gracefully near the surface. Their bright orange and white scales reflect beautifully in the water’s surface, creating a serene and calming effect.

On the right-hand side of the image, there is a small stone lantern with a traditional design. The lantern appears to be partially submerged in the pond, adding an element of rustic charm to the scene. Its reflection can also be seen on the water’s surface, enhancing the peaceful ambiance.

The overall atmosphere of the image conveys a sense of calm and tranquility, typical of a Japanese garden setting. The combination of natural elements like plants, water, fish, and stone lantern creates an inviting and harmonious environment.

The obvious problem is that the captions are long on feels and short on details.

So I changed the request and asked qwen2.5-vl-7b to try again:

Describe every significant element of the image in full detail.

The image showcases a serene and beautifully landscaped garden scene centered around a small pond. Here’s a detailed description of each significant element:

  1. Pond: The focal point of the image is a tranquil, shallow pond with clear water that reflects its surroundings. The surface of the water has gentle ripples, likely caused by the movement of fish or subtle breezes.

  2. Koi Fish: Two koi fish are visible in the pond. Their vibrant orange and white scales stand out against the muted tones of the water. They appear to be swimming near the surface, adding a dynamic element to the otherwise still scene.

  3. Stone Lantern: On the right side of the image is a traditional stone lantern partially submerged in the pond. The lantern has a classic design with multiple tiers and appears aged, giving it an authentic Japanese aesthetic. Its reflection can also be seen on the water’s surface, enhancing the visual harmony of the scene.

  4. Vegetation: Surrounding the pond are various plants and shrubs that contribute to the lushness of the garden. On the left side, there is a cluster of yellow flowers with green foliage, adding bright pops of color against the darker tones of other vegetation. The surrounding plants appear well-maintained but natural.

  5. Background Foliage: In the background, there are trees and bushes displaying autumnal colors, suggesting that this scene might be captured during fall. The leaves show shades of red, orange, and yellow, which contrast beautifully with the greenery around them.

  6. Stone Pathway: A stone pathway is visible on the left side leading to or from the pond area. It appears to be made up of large stones, blending seamlessly into the natural environment.

  7. Water Reflections: The water in the pond reflects both the koi fish and parts of the surrounding vegetation and structures, creating a mirror-like effect that enhances the peacefulness of the scene.

The overall composition of this image conveys a sense of tranquility and harmony, typical of traditional Japanese garden design principles such as balance (symmetry) and natural beauty. The interplay between water, stone elements, plants, and colors creates an inviting and calming atmosphere.

The results are much more plausible:

(the only one of these four I’d have taken is the last one; I’d have zoomed and reframed the first to get the steps either in or out, not halfway; I wouldn’t have cropped the top of the lantern in the second, and would have crouched to improve the angle; and I wouldn’t have tilted the camera in the third. I’d also have bumped the exposure at least half a stop for the first three; they’re dull)

Sadly, Qwen VL is infected with woke madness, and when asked to describe humans beings, it will completely leave out gender references by default, and if prodded will say things like “the person appears to be male” and use they/them pronouns. It may be possible to work around this with careful, explicit prompting.

Actually, it heavily overuses “appears to be” for all sorts of things, sigh. Kind of like how I overuse “actually”, actually.

Comments via Isso

Markdown formatting and simple HTML accepted.

Sometimes you have to double-click to enter text in the form (interaction between Isso and Bootstrap?). Tab is more reliable.