Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Small prototype with AI + generative sketching workflow. Sketches are written as usual in code, and prompts can be used to augment/modify the artwork's inputs and parameters. 🤖 This is using OpenAI API with GPT 3.5, already showing a surprisingly good grasp of color for an LLM.

Matt DesLauriers

61,056 subscribers

22,322 Aufrufe • vor 3 Jahren •via X (Twitter)

Bildung Wissenschaft & Technologie Kunst

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Matt DesLauriers

Matt DesLauriersvor 3 Jahren

This uses an interface/schema (for OpenAI to ensure a JSON response) so it can work on any type of parameters for your sketch—colors, shapes, text. So far, using AI for abstract tasks like generating new color palettes seems like a reasonable use case, but open to other ideas...

Profilbild von Emanuele Pasin

Emanuele Pasinvor 3 Jahren

I tried a couple of months ago using chatGPT to generate some palettes but those weren't so smooth. Do you give the prompt directly to chatGPT or is there something more running to smoothen the final colors?

Profilbild von Matt DesLauriers

Matt DesLauriersvor 3 Jahren

no post processing , these colors are direct result of openAI API call. Using their new functions/JSON features and a little prompt that basically is “give me 5 hex colors matching the input prompt X”

Profilbild von FHAS

FHASvor 3 Jahren

I started experimenting with generating different textures (with different color palettes) as a base for 2d/3d genart systems. Early days still but I see some very promising directions ahead.

Profilbild von William Mapan

William Mapanvor 3 Jahren

nice! ⚡️

Profilbild von // glitchstroke //

// glitchstroke //vor 3 Jahren

// i was trying some experiments with chatgpt a while back // asking it to generate color palettes in hex codes // and then make the whole palette a little warmer // and the like //// was really quite impressed //// what you have done here // is beautiful //

Profilbild von jiwa 🔆

jiwa 🔆vor 3 Jahren

very cool man 🙌

Profilbild von ilithya

ilithyavor 3 Jahren

🤩

Profilbild von henry

henryvor 3 Jahren

Really nice 👌

Profilbild von gde

gdevor 3 Jahren

It's like controlnet?

Profilbild von Matt DesLauriers

Matt DesLauriersvor 3 Jahren

Don’t know that , it’s just openAI GPT API at the moment!

Ähnliche Videos

Stop wasting LLM tokens on buggy code. 🤖 Introducing CoinGecko AI Prompts: The reliable way to guide your AI assistant to integrate with CoinGecko API. #BuildwithCoinGecko

Stop wasting LLM tokens on buggy code. 🤖 Introducing CoinGecko AI Prompts: The reliable way to guide your AI assistant to integrate with CoinGecko API. #BuildwithCoinGecko

CoinGecko

23,958 Aufrufe • vor 9 Monaten

This AI animation workflow is making a splash 💦 GPT Image 2 is available as a partner AI model in Adobe Firefly and it's perfect for animations like this. Check out the workflow and full prompts below 👇 #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

This AI animation workflow is making a splash 💦 GPT Image 2 is available as a partner AI model in Adobe Firefly and it's perfect for animations like this. Check out the workflow and full prompts below 👇 #AdobeFireflyAmbassadors #Ad #AdobePartnerModels

proper

67,541 Aufrufe • vor 1 Monat

Our first Generative AI short course in JavaScript! GitHub recently reported that JavaScript is again the world’s most popular programming language. To support web developers exploring and developing with generative AI, we just launched a new short course in JavaScript taught by Jacob Lee, founding engineer at . In Build LLM Apps with LangChain.js you’ll learn elements common in AI development, including: (i) Using data loaders to pull data from common sources such as PDFs, websites, and databases (ii) Prompts, which are used to provide the LLM context (iii) Modules to support RAG such as text splitters and integrations with vector stores (iv) Working with different models to write applications that are not vendor-specific (v) Parsers, which extract and format the output for your downstream code to process You’ll also build with the LangChain Expression Language, which lets you easily compose sequences (also called chains) of modules to perform complex tasks using LLMs. Putting all this together, you’ll also work on a conversational question-answering LLM application capable of using external data as context. Please sign up here:

Our first Generative AI short course in JavaScript! GitHub recently reported that JavaScript is again the world’s most popular programming language. To support web developers exploring and developing with generative AI, we just launched a new short course in JavaScript taught by Jacob Lee, founding engineer at . In Build LLM Apps with LangChain.js you’ll learn elements common in AI development, including: (i) Using data loaders to pull data from common sources such as PDFs, websites, and databases (ii) Prompts, which are used to provide the LLM context (iii) Modules to support RAG such as text splitters and integrations with vector stores (iv) Working with different models to write applications that are not vendor-specific (v) Parsers, which extract and format the output for your downstream code to process You’ll also build with the LangChain Expression Language, which lets you easily compose sequences (also called chains) of modules to perform complex tasks using LLMs. Putting all this together, you’ll also work on a conversational question-answering LLM application capable of using external data as context. Please sign up here:

Andrew Ng

284,275 Aufrufe • vor 2 Jahren

I'm a kinesthetic learner 🎓, so I often build basic versions of rad AI tools to grasp new concepts. This week's project is (unsurprisingly) giving an AI browser access. Sneak peek with Cloudflare Developers Browser Rendering + OpenAI GPT-4o 👇 Full video and code this weekend!

I'm a kinesthetic learner 🎓, so I often build basic versions of rad AI tools to grasp new concepts. This week's project is (unsurprisingly) giving an AI browser access. Sneak peek with Cloudflare Developers Browser Rendering + OpenAI GPT-4o 👇 Full video and code this weekend!

Ricky

11,068 Aufrufe • vor 1 Jahr

New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here:

New short course: DSPy: Build and Optimize Agentic Apps DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with Databricks and taught by Chen Qian, co-lead of the DSPy framework. Many AI builders spend hours hand-tuning prompts. When given a set of evals, DSPy automates this process. It’s especially useful for optimizing prompts, including few-shot prompts, in complex agentic AI workflows. Further, if you switch an application to a newer LLM, performance can degrade if your prompts were optimized to the previous model. DSPy automatically optimizes the entire system for the new LLM as well, using just a few evaluation examples. This course teaches DSPy works, and best practices for using it. You’ll write programs using DSPy’s signature-based programming model, debug them with MLflow tracing -- to gain visibility into how different parts of a pipeline, as well as how the overall system, are performing -- and automatically improve their accuracy with DSPy Optimizer. Please sign up here:

Andrew Ng

181,156 Aufrufe • vor 1 Jahr

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.

OpenAI just released access to Computer Use Agent via an API. It combines GPT-4o vision with advanced reasoning for an AI Agent to simulate controlling computer interfaces and performing tasks just like humans. You can try it for free using this Agent Playground.

Shubham Saboo

64,206 Aufrufe • vor 1 Jahr

We are getting closer to “Her” (part 2!) Conversationally do anything with emails, using LLM chaining & few-shot prompting for tool use ( inspired) This is now realtime (ish), thanks to #OpenAI gpt-3.5-turbo 🔈 on for voice realism! 🧵

We are getting closer to “Her” (part 2!) Conversationally do anything with emails, using LLM chaining & few-shot prompting for tool use ( inspired) This is now realtime (ish), thanks to #OpenAI gpt-3.5-turbo 🔈 on for voice realism! 🧵

Justin Alvey

481,039 Aufrufe • vor 3 Jahren

"Orgs and cos building MCP servers are taking an LLM-first approach to what the API needs to expose to the agent(s)." - Nikunj Handa from OpenAI "For example, Stripe has a bunch of APIs that can be used to create a subscription/customer/product/price. For an LLM, it can just combine that into a single function." "Instead of returning this massive JSON object, they can return something very specific to the task being solved, so that the LLM can more easily understand what's happening." "It's an opportunity to rewrite your APIs to be very LLM-first. Why do 2 hours of work, when you can do it in 4 lines of code under a minute?"

"Orgs and cos building MCP servers are taking an LLM-first approach to what the API needs to expose to the agent(s)." - Nikunj Handa from OpenAI "For example, Stripe has a bunch of APIs that can be used to create a subscription/customer/product/price. For an LLM, it can just combine that into a single function." "Instead of returning this massive JSON object, they can return something very specific to the task being solved, so that the LLM can more easily understand what's happening." "It's an opportunity to rewrite your APIs to be very LLM-first. Why do 2 hours of work, when you can do it in 4 lines of code under a minute?"

TBPN

11,445 Aufrufe • vor 1 Jahr

You can now generate and iterate on images with gpt-image-1.5 in Codex to create frontend designs, mockups, game assets, and more without leaving your workflow. Usage is included with your ChatGPT account, no API key needed.

You can now generate and iterate on images with gpt-image-1.5 in Codex to create frontend designs, mockups, game assets, and more without leaving your workflow. Usage is included with your ChatGPT account, no API key needed.

OpenAI

127,249 Aufrufe • vor 2 Monaten

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,571 Aufrufe • vor 9 Monaten

n8n's official Claude Code connector can now create and edit workflows! This goes way beyond plugging an API into MCP. It's purpose built for LLMs. Includes a new workflow TypeScript SDK so workflows are written as code instead of JSON, with more reliable validation. Works anywhere MCPs are supported (n8n 2.18.5+). 🔗 Full video:

n8n's official Claude Code connector can now create and edit workflows! This goes way beyond plugging an API into MCP. It's purpose built for LLMs. Includes a new workflow TypeScript SDK so workflows are written as code instead of JSON, with more reliable validation. Works anywhere MCPs are supported (n8n 2.18.5+). 🔗 Full video:

n8n.io

120,447 Aufrufe • vor 1 Monat

I'm building my own AI chat app in Cursor It can voice-to-text in your fav apps, with custom prompts. Can chat with gpt-4o, Claude, Gemini and even local/offline models like DeepSeek. Fully native written in SwiftUI. It's free with your API keys. Going to launch this week.

I'm building my own AI chat app in Cursor It can voice-to-text in your fav apps, with custom prompts. Can chat with gpt-4o, Claude, Gemini and even local/offline models like DeepSeek. Fully native written in SwiftUI. It's free with your API keys. Going to launch this week.

Meng To

37,404 Aufrufe • vor 1 Jahr

Browserbase just launched Director AI. It's an AI tool that can automate any web task using simple English prompts and generate repeatable automation code in one step. Like OpenAI Operator but free, with no coding required. +

Browserbase just launched Director AI. It's an AI tool that can automate any web task using simple English prompts and generate repeatable automation code in one step. Like OpenAI Operator but free, with no coding required. +

Shubham Saboo

21,166 Aufrufe • vor 1 Jahr

Can OpenAI Whisper and GPT 3.5 bring Voice Memos to the next level? Introducing Paxo ( an AI audio notes app purpose-built for meetings, journaling, and in-person conversations. Built with Rhythm Garg for fun. Turns out it’s… actually super useful.

Can OpenAI Whisper and GPT 3.5 bring Voice Memos to the next level? Introducing Paxo ( an AI audio notes app purpose-built for meetings, journaling, and in-person conversations. Built with Rhythm Garg for fun. Turns out it’s… actually super useful.

Miles McCain and 309 others

24,723 Aufrufe • vor 3 Jahren

$3️⃣ Computational Discovery An agentic prototype built with AlphaEvolve and Empirical Research Assistance to develop and score thousands of code variations in parallel. This can enable testing of new modelling approaches for complex fields like epidemiology in a fraction of the usual time.$

3️⃣ Computational Discovery An agentic prototype built with AlphaEvolve and Empirical Research Assistance to develop and score thousands of code variations in parallel. This can enable testing of new modelling approaches for complex fields like epidemiology in a fraction of the usual time.

Google DeepMind

22,451 Aufrufe • vor 1 Monat

It used to take weeks to make a LoFi animation like this. Now, with AI, you can create one in just 15 minutes. Music included. Full workflow with tools and prompts 🧵👇

It used to take weeks to make a LoFi animation like this. Now, with AI, you can create one in just 15 minutes. Music included. Full workflow with tools and prompts 🧵👇

TechHalla

45,862 Aufrufe • vor 11 Monaten

PSA: OpenAI is putting the Open back in OpenAI and Groq Inc has Day 0 support. 🤗 GPT-OSS 20B and 120B, hybrid-reasoning models with built-in browser search and code execution are now live for instant inference. P.S. We've also launched OpenAI Responses API compatibility.

PSA: OpenAI is putting the Open back in OpenAI and Groq Inc has Day 0 support. 🤗 GPT-OSS 20B and 120B, hybrid-reasoning models with built-in browser search and code execution are now live for instant inference. P.S. We've also launched OpenAI Responses API compatibility.

Hatice Ozen

80,584 Aufrufe • vor 10 Monaten