iiinova — where your digital self keeps evolving

CoffeeVectors @coffeevectors.bsky.social · 01/06/2025

Another dialog test with #Veo3! This time in a #darkfantasy setting with one of the characters as an #undead #witch Converted to #verticals with Luma Labs Reframe and upscale with Topaz Labs #aivideo #aicinema #aifilmmaking #aifilm #fantasy #dnd #lich

060

CoffeeVectors @coffeevectors.bsky.social · 28/05/2025

Using #Veo3 to try and recreate a the footstep flowers effect from Princess Mononoke (without the dying flowers). Then used @lumalabsai Reframe to turn the 16:9 into a #vertical. Upscaled in @topazlabs #aivideo #aifilm #verticals

130

CoffeeVectors @coffeevectors.bsky.social · 26/05/2025

My first test with Veo 3! Looking into over the shoulder dialog shots and emotional expressiveness. These are two text to vid prompts I cut together. It took a couple of tries to get two clips that paired up well. Having sound come with the video is definitely a game changer! #veo3 #aivideo #aifilm

010

CoffeeVectors @coffeevectors.bsky.social · 18/04/2025

Interesting how we went from people doing the robot to people acting like NPCs and game avatars.

010

CoffeeVectors @coffeevectors.bsky.social · 10/04/2025

Really impressed by chatGPT's new extended memory! It's mentioning context and ideas now that I'd normally have to manually feed it. Almost like I was continuing a chat rather than starting a new one. #chatGPT

000

CoffeeVectors @coffeevectors.bsky.social · 08/04/2025

Making the personalization profile for Midjourney 7 cracks me up. Do you prefer this picture of a pregnant woman or a closeup of a screaming bat? #midjourney

010

CoffeeVectors @coffeevectors.bsky.social · 06/04/2025

It’s interesting how a no/low code approach leveraged UI to abstract away having to know syntax. But now with LLMs, even though the code is imperfect and it helps to know how to debug and design architecture, I'm finding I want no/low UI with apps now. Is there an API? #aicoding

000

CoffeeVectors @coffeevectors.bsky.social · 03/04/2025

Just realizing you can access MCP servers in Windsurf! So it’s pretty simple to just switch between LLMs if you’re chatting with an SQL database and you want to see how the different models see things. I was just using Claude desktop but wanted to see if Gemini 2.5 was better. #mcp

000

CoffeeVectors @coffeevectors.bsky.social · 27/03/2025

Super impressed by chatGPT’s new image model! Here I’m testing how far I can push the handwriting with a fake drink recipe. For the calligraphy I uploaded a German manuscript from 1765. #aiart #aiartcommunity

120

CoffeeVectors @coffeevectors.bsky.social · 16/03/2025

Been trying to use the Blender MCP server to make some 3D scenes with Claude. Asked it to make a bowl and in trying to delete some existing geometry it ran a factory reset of the entire app. Luckily it was on a fresh Blender install. Be careful if you try it. #mcp

010

CoffeeVectors @coffeevectors.bsky.social · 12/03/2025

Learning how to use SQL and to analyze databases with Anthropic’s MCP. I’m new to this DB stuff so it’s been really eye opening. Here I had Claude Desktop make some animated charts from expenses tagged as transportation.🧵1/3 #sql #mcp #aicoding #dataanalysis

110

CoffeeVectors @coffeevectors.bsky.social · 09/03/2025

While I totally get the value in building apps without reading code, learning to read code/architecture has given me a huge new vocabulary for breaking down problems and understanding systems thinking outside of software. But it’s about as tough as learning a new language. #aicoding

000

CoffeeVectors @coffeevectors.bsky.social · 09/03/2025

Testing #HedraLabs new lip syncing Character 3 model on some #AImusic I made in #suno Ref images made in #magnifique and also upscaled for the closeups variations. Pretty incredible for just img&audio2vid! Camera zooms/editing/color -grade/grain in post. Upscaled to 4k. #aivideo #aifilmmaking

020

CoffeeVectors @coffeevectors.bsky.social · 08/03/2025

I want to see a movie like Flow, but with Godzilla. Like forget about the humans.

010

CoffeeVectors @coffeevectors.bsky.social · 07/03/2025

Haven’t been doing as much with the creative side of AI gen lately because I’ve been so focused on vibe coding and learning to code in general. Its already doing something because when new stuff comes out, using it isn’t nearly as intimidating or difficult to me as it used to be. #aicoding

000

CoffeeVectors @coffeevectors.bsky.social · 27/02/2025

Initial tests with Wan 2.1 14b text2video running locally in ComfyUI on a 3090. 1st vid was 20 steps and took 30 minutes. 2nd vid was 50 steps and took 80 minutes. Both were 1280x720 and using close to all 24GB of VRAM. Still messing with settings and different models. #aivideo #comfyui

120

CoffeeVectors @coffeevectors.bsky.social · 26/02/2025

Quick o3-mini deep research prompt asking for all AI releases in the past 7 days that can actually be used by a person or small business (with a powerful consumer GPU). Report includes release dates. Fast way to get up to speed if you’ve been working on other things. #deepresearch #chatGPT

000

CoffeeVectors @coffeevectors.bsky.social · 26/02/2025

Deep Research available in the regular chatGPT subscription! Nice!

010

CoffeeVectors @coffeevectors.bsky.social · 23/02/2025

Been loving this open source version of Deep Research by dzhng and reading the files in Frogmouth. Here I’m just asking what the best Gaussian Splat repos currently are. You can also manually paste the reports into an LLM and chat with it.

200

Reposted by CoffeeVectors

Ethan Mollick @emollick.bsky.social · 15/02/2025

This new paper shows people could not tell the difference between the written responses of ChatGPT-4o & expert therapists, and that they preferred ChatGPT's responses. Effectiveness is not measured. Given that people use LLMs for therapy now, this is an important (and urgent) topic for study.

712316

Reposted by CoffeeVectors

mr. TIM @timkellogg.me · 15/02/2025

Perplexity announced their own DeepResearch that includes a free tier and a generous $20/mo tier People who have tried both are finding the Perplexity version to be on par, perhaps better than OpenAI’s ($200/mo) Analysis of the Chernobyl drone strike yesterday: www.perplexity.ai/search/yeste...

perplexity.ai

yesterday a drone hit the Chernobyl nuclear power plant. Please investigate if...

The recent drone strike on the Chernobyl Nuclear Power Plant’s protective containment structure has reignited global concerns about nuclear safety amid the...

5258

CoffeeVectors @coffeevectors.bsky.social · 08/02/2025

Testing how #Veo2 handles liquids & fabrics. In post I added some zooming, speed ramping, some occasional focus blur and a little color grade, but these shots are basically out of the box. The rain, lens flares, splashes and slow motion were prompted. (Music: Suno) 🧵 1/3 #aivideo #aifilm

110

CoffeeVectors @coffeevectors.bsky.social · 05/02/2025

Was chatting with R1 about simulation theory and it brought up the idea of the creators of the sim being in a sim themselves, that the base reality might be the infinite ladder of nested sims. Like a vertical multiverse. I wonder if you could make this into a game mechanic?

000

Reposted by CoffeeVectors

Ethan Mollick @emollick.bsky.social · 03/02/2025

wrote about Deep Research, which is very, very good at doing nuanced and complex research. It is also the first narrow agent that can do sophisticated and likely quite economically valuable work, which tells us something important about the future. open.substack.com/pub/oneusefu...

open.substack.com

The End of Search, The Beginning of Research

The first narrow agents are here

19716

CoffeeVectors @coffeevectors.bsky.social · 02/02/2025

Took a simple fluid sim scene that I set up in Blender using a python script made in o3-mini. And then I ran it through several styles with vid2vid in Runway ML 🧵1/5 #aivideo

111

CoffeeVectors @coffeevectors.bsky.social · 02/02/2025

Asked o3-mini to make a quick water sim with an orbiting camera in Blender 4.3 using a python script. This took a few tries and some tweaking so it’s not a one shot. I’m optimistic this will improve down the road. Prompt below. #o3mini #aicoding #blender #fluidsim

130

CoffeeVectors @coffeevectors.bsky.social · 01/02/2025

Got o3-mini and a distilled R1-14b local model running in a custom cozy UX I built in Windsurf. I can change the BG with links to Gify, blur them, & change brightness. I’m doing these projects mainly to learn coding with AI and to get better at making my own tools. #aicoding

120

CoffeeVectors @coffeevectors.bsky.social · 25/01/2025

Was building a custom chat UX for AI models and I didn’t realize the API is stateless and you have to keep sending it chat history. (Obvs correct me if I’m wrong.) But now I’m starting to get why AI sometimes erases a bunch of your code or gets lost if your chat is too long. #aicoding

010

CoffeeVectors @coffeevectors.bsky.social · 22/01/2025

Really interesting reading #deepseekr1 reasoning text. One critique of AI is its ability to confidently tell you hallucinations, but the reasoning text tends to bring up what its unsure of. Here I asked it what “warped noise” was and it didn’t seem to really know. 🧵1/3 #ai

120

Reposted by CoffeeVectors

Ethan Mollick @emollick.bsky.social · 20/01/2025

The raw chain of thought from DeepSeek is fascinating, really reads like a human thinking out loud. Charming and strange.

1116215

CoffeeVectors @coffeevectors.bsky.social · 13/01/2025

Any opinion on which AI models are best for sentiment analysis on social media comments? I’ve got a list of hugging face models I’m testing but just curious what everyone thinks. #aicoding

020

CoffeeVectors @coffeevectors.bsky.social · 04/01/2025

The more I work with AI on coding, the more novel it seems as a relationship. It’s the teacher, explaining complex concepts to me. It’s a new employee making mistakes. It’s the miracle worker, solving problems that were confusing me. Sometimes we’re both lost at sea, yelling at the code. #aicoding

140

CoffeeVectors @coffeevectors.bsky.social · 28/12/2024

Has anyone been trying @deepseek_ai v3 for coding? I’m still messing around with it, but how do you feel it compares to o1 and Sonnet 3.5? #aicoding

010

CoffeeVectors @coffeevectors.bsky.social · 25/12/2024

Watching a small ML course on Udemy and I don’t always understand the code or explanation. Been using chatGPT vision to look at some of the content I don’t get and have it answer my questions. Feels like bringing my own interface layer to what would normally be a one way video.

040

Reposted by CoffeeVectors

CoffeeVectors @coffeevectors.bsky.social · 17/12/2024

Edited this using AI video clips from Google’s new #Veo2! I was able to use them like the real footage I usually shoot for my fashion/makeup clients. There’s post with the vfx/grain/speed, but the Veo2 clips were great out of the box. Music is Suno v4. #aivideo #aifashion #aifilmmaking #aiart

0121

CoffeeVectors @coffeevectors.bsky.social · 17/12/2024

0121

CoffeeVectors @coffeevectors.bsky.social · 17/12/2024

First test with Google’s Veo 2! Was curious how it handled animating an AI illustration with their text2img2video pipeline. Interesting how it has character consistency but the environment and other elements sometimes shifts. Love that it makes 4 videos! 🧵 #veo2 #aivideo #aiart #aifilmmaking

120

Reposted by CoffeeVectors

Shura @shurastei.bsky.social · 14/12/2024

Is this the reality? #AIart

1454

Reposted by CoffeeVectors

CoffeeVectors @coffeevectors.bsky.social · 14/12/2024

Used Pika Labs 2’s new ingredients feature to make the top video. Then did vid2vid with it in Sora (1080p Mild Remix). Second clip is the same videos, just zoomed in. Ingredients in 🧵#aivideo #aifilmmaking #aiart #aiartcommunity #sora #pikalabs #soraai #pikavids #lostatsea

151

CoffeeVectors @coffeevectors.bsky.social · 15/12/2024

Just got access to chatGPT Vision! Works as I expect. Kind of interesting tho because it’s also on the Vision Pro app, but on there it’s telling me it can’t read text or look through the pass thru cameras. But it can see my virtual environments.

020

CoffeeVectors @coffeevectors.bsky.social · 14/12/2024

151

CoffeeVectors @coffeevectors.bsky.social · 14/12/2024

Using Gemini 2 to walk me thru Blender and Unity interfaces is wild! A live instruction manual. Its even more interesting when you think about how it’s not a product specifically designed for the program.

040

CoffeeVectors @coffeevectors.bsky.social · 14/12/2024

So I decided to buy the pro plan for Sora and also check out the new Pika Labs 2.0. Have to say Sora is pretty challenging to use. Pika works intuitively out of the box and has impressive control and results. My literal first try with ingredients.🧵 #aivideo #aifilmmaking #aiart

180

CoffeeVectors @coffeevectors.bsky.social · 10/12/2024

“Medusa, mi amor” Quick test & edit with clips from Sora along with music from Suno v4 and some sfx from Eleven Labs #sora #soraai #aivideo #aiart #aifilmmaking #medusa #greekmythology #aimusic

060

CoffeeVectors @coffeevectors.bsky.social · 09/12/2024

Is anyone using the MiniMax/Hailuo API? Been using piapi for the Kling API. #aivideo

010

CoffeeVectors @coffeevectors.bsky.social · 26/11/2024

You ever talk with chatGPT about something mundane and accidentally discover profound truths about the universe? It’s like damn, I was just trying to understand how some code worked.

392

CoffeeVectors @coffeevectors.bsky.social · 26/11/2024

Made a synthwave remix of a Stone Temple Pilots song with #suno v4. Video is #hailuoAI from a #midjourney image. Prompt was “music video” with prompt refinement on and doing a few takes. Upscaled in Topaz. #aiart #aimusic #aivideo #aimusicvideo

4273