Загрузка видео...

Не удалось загрузить видео

На главную

Did some experiments with local models In this example, all requests are handled by Gemma 4. It generates a new circuit as JSON based on the prompt Edited out the waiting times from the clip. It usually takes around 5 - 10s More details ↓

DilumSanjaya's profile picture

Dilum Sanjaya

55,014 subscribers

82,137 просмотров • 2 месяцев назад •via X (Twitter)

ИскусствоОбразованиеНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

More experiments of this workflow: Generating quick 3d models using Lumas Genie 3D. A text prompt generates 4 models in 10 seconds. Then, using Lumas webviewer, I feed a screencapture of the model into Krea ai which details the model based on another prompt. Finally, Magnific AI is used to add the final finish. The Santa mechs are insanely refined😱 Check out the final "Renders" below. #3d #ai
0:58

More experiments of this workflow: Generating quick 3d models using Lumas Genie 3D. A text prompt generates 4 models in 10 seconds. Then, using Lumas webviewer, I feed a screencapture of the model into Krea ai which details the model based on another prompt. Finally, Magnific AI is used to add the final finish. The Santa mechs are insanely refined😱 Check out the final "Renders" below. #3d #ai

Martin Nebelong

88,148 просмотров • 2 лет назад

🚨 Breaking - Buga UFO Sphere of Colombia Update - Experiments have been carried out on the Buga Sphere: According to the experiments When the sphere is rotated it allegedly generates antigravity More details in the comments #ufotwitter #Bugasphere #ZPE #Ufox #Uapx
3:40

🚨 Breaking - Buga UFO Sphere of Colombia Update - Experiments have been carried out on the Buga Sphere: According to the experiments When the sphere is rotated it allegedly generates antigravity More details in the comments #ufotwitter #Bugasphere #ZPE #Ufox #Uapx

T R U T H P O L E

344,299 просмотров • 8 месяцев назад

Bringing open models into the physical world. Check out this vibrant local assistant build from the Gemma 4 Good Hackathon. YANVI runs Gemma 4 locally on edge hardware, featuring a physical presence, an expression engine, and full desktop autonomy.
1:26

Bringing open models into the physical world. Check out this vibrant local assistant build from the Gemma 4 Good Hackathon. YANVI runs Gemma 4 locally on edge hardware, featuring a physical presence, an expression engine, and full desktop autonomy.

Google Gemma

23,522 просмотров • 1 месяц назад

This clip is a perfect example of how Russian propaganda works: 1) It takes a real article from the Financial Times. 2) Uses some parts of it as-is. 3) Rephrases other parts to make it sound as though Putin has a leg to stand on. 4) Completely omits one of the article’s main points: that Putin has no real understanding of what is actually happening at the front. Link to the Financial Times article Skabeeva is quoting:
0:48

This clip is a perfect example of how Russian propaganda works: 1) It takes a real article from the Financial Times. 2) Uses some parts of it as-is. 3) Rephrases other parts to make it sound as though Putin has a leg to stand on. 4) Completely omits one of the article’s main points: that Putin has no real understanding of what is actually happening at the front. Link to the Financial Times article Skabeeva is quoting:

Natalka

23,371 просмотров • 4 месяцев назад

A simple litmus test to find good altcoins setup Watch for the ones that fully retrace their 10/10 wick and build a clean base around it. These are usually the cleanest R/R trades on the board imo. For example, look at the PA on these: • $HYPE • $AERO • $WLD, $JTO, $INJ and others All of them retraced the wick → based around it → pulled a 2-3x. There are still a few underrated setups in play. Some are already basing. Some are just nearing their 10/10 wicks . All you gotta do is spot them early 4
0:27

A simple litmus test to find good altcoins setup Watch for the ones that fully retrace their 10/10 wick and build a clean base around it. These are usually the cleanest R/R trades on the board imo. For example, look at the PA on these: • $HYPE • $AERO • $WLD, $JTO, $INJ and others All of them retraced the wick → based around it → pulled a 2-3x. There are still a few underrated setups in play. Some are already basing. Some are just nearing their 10/10 wicks . All you gotta do is spot them early 4

Axel Bitblaze 🪓

17,046 просмотров • 2 месяцев назад

$BTC HAS NEVER BROKEN ITS 4-YEAR CYCLE And right now we're in the final phase - Bear Market 2014, 2018, 2022 - three times this played out the same way Based on the previous two cycles - October 2026 is where this ends Personally, I'm not fighting this phase. I'm waiting it out What about you - are you fighting it or waiting it out? FOLLOW + NOTIFS ON!
0:40

$BTC HAS NEVER BROKEN ITS 4-YEAR CYCLE And right now we're in the final phase - Bear Market 2014, 2018, 2022 - three times this played out the same way Based on the previous two cycles - October 2026 is where this ends Personally, I'm not fighting this phase. I'm waiting it out What about you - are you fighting it or waiting it out? FOLLOW + NOTIFS ON!

bee🐝

46,517 просмотров • 4 месяцев назад

putting the Claude Agent SDK to the test with an Ad Agent - finds competitors, learns from their ads - prompts and generates on brand creatives - packages it in a shareable report I can run this autonomously or with a prompt. no node based workflows needed
17:45

putting the Claude Agent SDK to the test with an Ad Agent - finds competitors, learns from their ads - prompts and generates on brand creatives - packages it in a shareable report I can run this autonomously or with a prompt. no node based workflows needed

The Boring Marketer

77,600 просмотров • 8 месяцев назад

Clip from this week’s podcast looking at free taking times from some players after Darragh McCarthy’s free taking came in for some criticism Turns out his routine takes a little less than TJ Reid on average and around the same as Mark Rodgers. Much of a muchness #GAA
1:46

Clip from this week’s podcast looking at free taking times from some players after Darragh McCarthy’s free taking came in for some criticism Turns out his routine takes a little less than TJ Reid on average and around the same as Mark Rodgers. Much of a muchness #GAA

Paul Carroll

27,944 просмотров • 7 месяцев назад

From a simple prompt to a fully consistent 15s scene with 4 shots, using the new Kling 3.0 workflow on fal 🎥 Try it out:
0:24

From a simple prompt to a fully consistent 15s scene with 4 shots, using the new Kling 3.0 workflow on fal 🎥 Try it out:

Blendi

12,994 просмотров • 6 месяцев назад

Ok, so the new Midjourney Style Tuner is here and it's a MASSIVE update. There is so much to unpack, no way I can do it all in one post, but here is an overview. You start by typing in /tune followed by your prompt. MJ will generate a range of sample images (between 16-128) showing different visual styles based on your prompt. Then you choose your favorite images from the sample to generate a unique code you can use to customize the look of future jobs. (link below) So for example, I just tried it with the prompt: 💬 1990s, a photo of a woman dressed in fuzzy velour, shimmering midnight hues reflecting sadness by the lake, a contemporary nightmare on cross-processed film --ar 4:5 --c 4 I selected 10 images, which generated the code zlPhgLCHDXol64kPlwSUzu97. I can then add it to my prompt using --style {code} But it makes more sense if you try it yourself, so try playing around with my Style Tuner for that prompt and generate your own code from your selections: Some quick notes: -You can control the level of style applied by adding the --s parameter to your prompt. -You can combine multiple styles together by separating with a hyphen, i.e --style code1-code2 I will be obsessing over this all day tomorrow and sharing everything I learn along the way. This is an incredible update.
0:42

Ok, so the new Midjourney Style Tuner is here and it's a MASSIVE update. There is so much to unpack, no way I can do it all in one post, but here is an overview. You start by typing in /tune followed by your prompt. MJ will generate a range of sample images (between 16-128) showing different visual styles based on your prompt. Then you choose your favorite images from the sample to generate a unique code you can use to customize the look of future jobs. (link below) So for example, I just tried it with the prompt: 💬 1990s, a photo of a woman dressed in fuzzy velour, shimmering midnight hues reflecting sadness by the lake, a contemporary nightmare on cross-processed film --ar 4:5 --c 4 I selected 10 images, which generated the code zlPhgLCHDXol64kPlwSUzu97. I can then add it to my prompt using --style {code} But it makes more sense if you try it yourself, so try playing around with my Style Tuner for that prompt and generate your own code from your selections: Some quick notes: -You can control the level of style applied by adding the --s parameter to your prompt. -You can combine multiple styles together by separating with a hyphen, i.e --style code1-code2 I will be obsessing over this all day tomorrow and sharing everything I learn along the way. This is an incredible update.

Nick St. Pierre

377,975 просмотров • 2 лет назад

NEW: Danny Stone details a prime example showing how The Green Party deals with antisemitism - by not dealing with it at all for two years.
1:02

NEW: Danny Stone details a prime example showing how The Green Party deals with antisemitism - by not dealing with it at all for two years.

Adam Cailler

16,736 просмотров • 4 месяцев назад

Before this clip, u literally have to do this at least 4-5 times. The game teaches you music note sheet appears = Music activation. Navi gets close to the triforce in this clip as well. JINGLE plays on ALL of those instances when you are in right spot. U can here it in this clip.
0:33

Before this clip, u literally have to do this at least 4-5 times. The game teaches you music note sheet appears = Music activation. Navi gets close to the triforce in this clip as well. JINGLE plays on ALL of those instances when you are in right spot. U can here it in this clip.

2sallads

142,449 просмотров • 6 дней назад

Emir Han Spot on, Sally Field’s character was straight-up insufferable! This clip from the movie where 'Jump Around' plays takes the over-the-top family chaos to a whole new level Perfect example of why some parents just can’t handle the fun!
2:07

Emir Han Spot on, Sally Field’s character was straight-up insufferable! This clip from the movie where 'Jump Around' plays takes the over-the-top family chaos to a whole new level Perfect example of why some parents just can’t handle the fun!

Popcultureguy

19,956 просмотров • 6 месяцев назад

Ok... I'm not going to hate on the music but... Hearing this in game all the time as a main theme would get annoying very very quickly. edited example of it in game:
0:57

Ok... I'm not going to hate on the music but... Hearing this in game all the time as a main theme would get annoying very very quickly. edited example of it in game:

Flowi

212,943 просмотров • 1 год назад

A completely local agent that lives right inside your pocket. 📱 Watch Gemma 4 run 100% locally in the Google AI Edge Gallery app. It converts images into JSON schemas, transcribes audio, and uses agent skills to interact with apps, all entirely offline.
3:20

A completely local agent that lives right inside your pocket. 📱 Watch Gemma 4 run 100% locally in the Google AI Edge Gallery app. It converts images into JSON schemas, transcribes audio, and uses agent skills to interact with apps, all entirely offline.

Google Gemma

88,541 просмотров • 3 месяцев назад

In-world AI generated scene from scratch! No external tools were used (blender, vscode etc). I simply typed things like `/create scarecrow` or `/edit make bees fly around it` and the AI handled it. The whole session was around 12 minutes, most creations and edits took <10s and while they were happening I just went and duplicated and placed things around. The AI models will get better. Right now there's some confusion where AI gets angles inverted etc, but this all seems fixable. Currently using anthropic API for speed, but I found GPT-5 makes better models but it takes much longer to generate.
0:30

In-world AI generated scene from scratch! No external tools were used (blender, vscode etc). I simply typed things like `/create scarecrow` or `/edit make bees fly around it` and the AI handled it. The whole session was around 12 minutes, most creations and edits took <10s and while they were happening I just went and duplicated and placed things around. The AI models will get better. Right now there's some confusion where AI gets angles inverted etc, but this all seems fixable. Currently using anthropic API for speed, but I found GPT-5 makes better models but it takes much longer to generate.

Ash

16,561 просмотров • 1 год назад