Discover and read the best of Twitter Threads about #DallE
Most recents (24)
🐍 #Script en #python para crear contenidos con imágenes y vídeo por #IA en #WordPress con tecnología de #Openai (#GPT)
Mediante un fichero csv generas un contenido por cada keyword adjunta.
Os cuento el proceso que sigue el script👇
(enlace al final del hilo).
Mediante un fichero csv generas un contenido por cada keyword adjunta.
Os cuento el proceso que sigue el script👇
(enlace al final del hilo).
Lo primero que realiza es un análisis de qué es lo que está posicionando en top 10 para la #keyword sobre la que se va a trabajar.
Se revisan los #titles, #descriptions, #h1, #h2, #h3, #h4, #h5 y #h6.
Todo este análisis se hace por separado, y luego se une.
Se revisan los #titles, #descriptions, #h1, #h2, #h3, #h4, #h5 y #h6.
Todo este análisis se hace por separado, y luego se une.
Después de definir la partes principales y la #estructura, se empieza a desarrollar el texto por partes.
Desarrollar el #texto por partes tiene su motivo.
Si le doy la estructura completa a la #IA, responde siempre con un sólo párrafo normalmente.
Desarrollar el #texto por partes tiene su motivo.
Si le doy la estructura completa a la #IA, responde siempre con un sólo párrafo normalmente.
Yapay zeka asistan mı yoksa akıl hocası mı? Belki de her ikisi de! Günlük hayatımızdan iş hayatına, eğitimimize kadar birçok alanda yapay zeka uygulamalarını kullanabiliriz. #YapayZeka #AkılHocası #İşHayatı #Eğitim #Teknoloji #Gelecek #Yenilikçilik
#ChatGPT
#ChatGPT
chat.openai.com/chat ChatGPT orjinal sitesi. GPT-3.5 versiyonu ücretsiz 2021 yılına kadar verdi işlemektedir. GPT-4 yeni versiyonudur ve güncel veriyi içermektedir, ücretlidir. #ChatGPT #chatgpt4
chatspot.ai ücretsiz, yazı, konuşma ve resim çizdirme sitesi #chatspot
MidJourney v5 vs DALLE-2 🥊
Without fancy prompts, which AI produces the best images?
(midjourney images shown first)
Without fancy prompts, which AI produces the best images?
(midjourney images shown first)
A lake house on the moon
An underground forest lit up by fireflies
🔥Anime AI Model🔥
DucHaitenClassicAnime is a custom AI model great for classic anime and is available on mage.space
View examples here: mage.space/u/DucHaitenCA
#stablediffusion #aiia #aiart #midjourney #dalle
👇🧵
DucHaitenClassicAnime is a custom AI model great for classic anime and is available on mage.space
View examples here: mage.space/u/DucHaitenCA
#stablediffusion #aiia #aiart #midjourney #dalle
👇🧵
lady
gentleman
ICYMI - I made an AI-generated deck builder over the weekend 🔥
3 versions:
📊 Startup Description > Pitch Deck
👩🏫 Prompt > Lesson Slides (#education)
📚 Topic > Illustrated children's story
Check them out 🔻
3 versions:
📊 Startup Description > Pitch Deck
👩🏫 Prompt > Lesson Slides (#education)
📚 Topic > Illustrated children's story
Check them out 🔻
📊 Startup Description > Pitch Deck
Here's the first thread, where you can see it evolving over time.
1) First, generated title + body text w #gpt3
2) Added AI selected color
3) Added AI selected font
4) Added #dalle image
Here's the first thread, where you can see it evolving over time.
1) First, generated title + body text w #gpt3
2) Added AI selected color
3) Added AI selected font
4) Added #dalle image
👩🏫 Prompt > Lesson Slides (#education)
Here's "AutoLessons", for generating lesson slides.
Examples in thread.
Here's "AutoLessons", for generating lesson slides.
Examples in thread.
We had an AMAZING session with @UntappedVC LPs this morning on the "Future of AI in VC".
Here's an abbreviated version as a Twitter thread!
👇
Here's an abbreviated version as a Twitter thread!
👇
To set the stage, here's our job as a VC.
- Strategy: Thesis, portfolio construction, etc.
- Fundraise: LP comms, fund mgmt
- General Ops: Marketing, legal, HR, etc.
- Investing breaks down into: Source, Decide, Win, Support
- Strategy: Thesis, portfolio construction, etc.
- Fundraise: LP comms, fund mgmt
- General Ops: Marketing, legal, HR, etc.
- Investing breaks down into: Source, Decide, Win, Support
History of AI in VC
AI in VC isn't new, but it's primarily been in two areas.
AI in VC isn't new, but it's primarily been in two areas.
Playing around with AI-generated, non-existent movies and the idea of #ArtificialNostalgia, I started thinking about the notion of ›vibe,‹ how it might describe what I'm looking for in these images and what distinguishes it from concepts like ›style‹ or ›mood‹
1/16
1/16
Much of the discussion around AI-generated images has involved questions of style, and for good reason. »In the style of ...« is maybe the most common phrases used in prompts, as #DallE, #Midjourney, and #StableDiffusion promise to produce images in any possible style
2/16
2/16
This category of style transcends cultural hierarchies: Style can mean the brushstroke of a painter, the visual qualities of historical technical media, or the look of certain games & TV shows: Van Gogh, Polaroid, Unreal Engine, or Southpark – everything becomes a ›style‹
3/16
3/16
Just 6 months ago Twitter was flooded with Tweets about #dalle. Then came #midjourney and #stablediffusion. 2 months ago, #chagpt exploded. Now the chatter mostly died down. I wonder if you weren't on Twitter, would you know of these novelties?
I don't know how these technologies captured users' attention on another social media platform. LensaAI exploded elsewhere, but I'm unaware of where. Information bubbles exist across platforms as the exist within platforms.
We make the mistake that true novelties are not novel anymore because we were exposed too early in the adoption cycle. Image2Text is not novel enough anymore to warrant a tweet! But what effect is this on people who were never exposed to it? It's as if that novelty never existed.
Playing with diffusion models leads to the awareness of concepts without words to describe them. Today, words don't precisely control image generation, but I expect this to improve over time. Soon, we might be expanding our vocabulary by generating #aiart!
Our interaction changes with every new version of the AI product. How one prompts in #dalle2 is different from #midjourney. Each version of MidJourney requires different prompting. Each finetuned model of #stablediffusion also prompts differently. Prompting has no standards.
The constraints that drive the generation of an image depend on the relationship between many variables. The relationship of words in a prompt, the strength of knobs, the iteration between images, the iteration between models, and the overall sequence of itself.
Quand j'ai commencé dans le marketing et l'éditorial, #OpenAIChatGPT et #midjourneyAi n'existaient pas. Nous n'en étions plus à la machine à écrire et au noir & blanc. Mais quand même... Du coup, voilà ce que j'aurais fait si je m'étais lancé dans le game avec ces outils. 🧶
1 - La découverte brute
Quelle putain d'invention les amis ! Imaginez un peu tout ce qu'on peut faire avec de tels outils... Et c'est justement ce que j'aurais voulu savoir en premier lieu : Les possibilités.
Quelle putain d'invention les amis ! Imaginez un peu tout ce qu'on peut faire avec de tels outils... Et c'est justement ce que j'aurais voulu savoir en premier lieu : Les possibilités.
Sur #ChatGPT, j'aurais tenté d'écrire un sonnet sur la chute du Mordor... avec Mister Bean en héros principal (true story). J'aurais cherché à tester ses connaissances en physique des particules ou en astronomie (true story, volume 2).
It is a curious and odd coincidence that the Yin and Yang mirrors the duality that C.S.Peirce identified in semiotics as icons and symbols.
Even more surprising (and useful) is that you can actually explore this duality by playing around with diffusion models (i.e., #stablediffusion, #dalle, #midjourney). This is because these models are both symbolic as well as iconic in nature. medium.com/intuitionmachi…
It's also intriguing that existing human civilization is structured primarily around the use of symbols. An insightful ancient historical accounting of this can be found in the book "Alphabet versus the Goddess". amazon.com/Alphabet-Versu…
🟣 Tome is the A.I.-powered “storytelling” app (powerpoint competitor?) launched by a startup composed of veterans of Meta’s product teams that hope to build useful business software powered by generative A.I.
Thread:
#ai #artificialintelligence #dalle2 #openai #dalle #tomeapp
Thread:
#ai #artificialintelligence #dalle2 #openai #dalle #tomeapp
ℹ️ They just released their new killer feature: prompt-to-deck:
• Type in a prompt and watch Tome generate entire narratives from scratch or create additional content pages within seconds.
• Type in a prompt and watch Tome generate entire narratives from scratch or create additional content pages within seconds.
• Use their Dall-E 2 tile to create compelling images, tailor-made to bring your idea to life.
• Drag-and-drop creation, responsive pages, and one-click themes mean you don’t waste time aligning content or applying brand colors.
• Drag-and-drop creation, responsive pages, and one-click themes mean you don’t waste time aligning content or applying brand colors.
In this thread, I'll be showcasing the impressive content generation capabilities of #ChatGPT, the new language model from @OpenAI that has taken the world by storm this week.
It can do wonders in a wide range of applications. Here are 30 ace use cases you'll be amazed by!
👇🧵
It can do wonders in a wide range of applications. Here are 30 ace use cases you'll be amazed by!
👇🧵
To start off, who hasn't dreamed of being a tech reviewer like Marques Brownlee?
If you're up for writing tech guides, try writing them with a lyrical twist!
Steve Bannon hizo presidente a Trump en 2017, popularizando una forma de atraer y convertir personas a la ultraderecha que llegó para quedarse y que cada vez tiene más y mejores herramientas.
Nuestras hijas, nuestros hijos, están siendo víctimas y necesitan ayuda 🧵
Nuestras hijas, nuestros hijos, están siendo víctimas y necesitan ayuda 🧵
Mi hija tiene 12 años. Hasta este año, su madre y yo nos hemos negado a que tuviese móvil.
El resto de niños y niñas de su curso (tres líneas), no solo tienen móvil desde hace dos años como mínimo, sino que además están en todas las redes sociales: Instagram, TikTok, BeReal, Snapchat…
So I may have asked @OpenAI's new ChatGPT to reimagine the show Friends as a seven-episode Netflix mystery thriller set in New York City... The following is written and storyboarded entirely by #AI #ChatGPT #dalle 🧵1/32
The show opens with a scene of Emily, a friend and neighbor of the group, being murdered in her apartment. This sets the tone for the show and introduces the central mystery that will be explored throughout the season. 2/32
We meet the main characters - Rachel, Monica, Phoebe, Joey, Chandler, and Ross - as they go about their lives in New York City. As the friends learn of Emily's death, they are shocked and saddened. They come together and decide to investigate the murder on their own. 3/32
🤖 Is this the first AI x AR x Haptics IG filter?
📚 I spent this weekend learning @metaspark from scratch to create this “Augmented Flyer” filter.
I received inspiration & feedback from friends like @DonAllenIII and @Enuriru, and even included a soundtrack from @guskamp!
🧵🧵
📚 I spent this weekend learning @metaspark from scratch to create this “Augmented Flyer” filter.
I received inspiration & feedback from friends like @DonAllenIII and @Enuriru, and even included a soundtrack from @guskamp!
🧵🧵
ℹ️ Let’s break it down:
• The experience starts with a scan of your surrounding (playing an ambient sound)
• Once your phone finds a flat surface (floor or wall), a grid appears, allowing you to tap anywhere to place the flyer
• The experience starts with a scan of your surrounding (playing an ambient sound)
• Once your phone finds a flat surface (floor or wall), a grid appears, allowing you to tap anywhere to place the flyer
• Taping on the screen triggers my signature sound & a short vibration
• You can use two fingers to rotate the flyer (and it will trigger a custom haptic feedback via a script that I wrote)
• Once placed, the flyer plays an animation (multiple images generated with @OpenAI).
• You can use two fingers to rotate the flyer (and it will trigger a custom haptic feedback via a script that I wrote)
• Once placed, the flyer plays an animation (multiple images generated with @OpenAI).
1/ 🚀 Officially launching productsby.ai
Create, Explore & Shop A.I. generated products.
Pinterest & Amazon for A.I. generated goods.
Have a brand/company? We'll generate you unique swag for your co: productsby.ai/swag
DEMO
loom.com/share/c408af6c…
Create, Explore & Shop A.I. generated products.
Pinterest & Amazon for A.I. generated goods.
Have a brand/company? We'll generate you unique swag for your co: productsby.ai/swag
DEMO
loom.com/share/c408af6c…
2/ Go ahead and try it out - it's free to explore & create new products at the moment!
This website was built out over the past few days. Primarily on top of @openai's #dalle api.
This website was built out over the past few days. Primarily on top of @openai's #dalle api.
3/ The logo I picked for productsby.ai is just a chair in the style of Salvador Dali - and it's pretty dope!
🧵Automated image generation with DALL-E
1. A few days ago @OpenAI announced that #DALLE users could create images programmatically via API.
To celebrate we took a vintage shot of @eerac, circa 2012, and through in a healthy assortment of fully automated AI whimsey.
1. A few days ago @OpenAI announced that #DALLE users could create images programmatically via API.
To celebrate we took a vintage shot of @eerac, circa 2012, and through in a healthy assortment of fully automated AI whimsey.
2. Until two days ago, DALL-E users have only ever been able to generate images through @OpenAI's website, labs.openai.com
DALL-E delivers great image quality, but without being able to use it programmatically, it's cumbersome to incorporate in to automated workflows.
DALL-E delivers great image quality, but without being able to use it programmatically, it's cumbersome to incorporate in to automated workflows.
3. In August, @StabilityAI's open release of #stablediffusion led to an explosion in 3rd party tools built on text-to-image AI.
While @OpenAI hasn't released their network, they have introduced a way to incorporate DALL-E in to workflows and plugins.
While @OpenAI hasn't released their network, they have introduced a way to incorporate DALL-E in to workflows and plugins.
It's pretty fast!
Need to get rate limit higher though, they only let me do 10 per minute.
Need to get rate limit higher though, they only let me do 10 per minute.
Results aren't always "great", but these are cool too
I designed 160 weapons for a heroic fantasy game, inspired by World of Warcraft... in just a few minutes.
A short thread on Generative AI & gaming 🧵
#GenerativeAI #AI #StableDiffusion #Dreambooth #Midjourney #Dalle #Gaming #UGC
A short thread on Generative AI & gaming 🧵
#GenerativeAI #AI #StableDiffusion #Dreambooth #Midjourney #Dalle #Gaming #UGC
Generative AI is likely to go big in vertical communities such as gaming, per @Tocelot - “The fringe is where revolutions start”.
AI can help design and quickly create new gaming environments, textures, scenes, characters, weapons, skins... or props.
AI can help design and quickly create new gaming environments, textures, scenes, characters, weapons, skins... or props.
@Tocelot Dalle, Midjourney or StableDiffusion generate exquisite images. However, it’s challenging to reconstruct specific subjects while maintaining high fidelity to their key visual features. Even w dozens of detailed iterations, the outcome is rarely consistent. Prompting is daunting…
Day 260 of #Blender3d| #b3d
I generated an image using #stablediffusion and #DALLE 2
I put the image into #ICON to turn it into a 3D model.
Then I used #mixamo to animate the model. (Then did a little extra thing with Blender) Details below!
I generated an image using #stablediffusion and #DALLE 2
I put the image into #ICON to turn it into a 3D model.
Then I used #mixamo to animate the model. (Then did a little extra thing with Blender) Details below!
How I did it:
1️⃣ Generate Image Using @playground_ai which has both #DALLE & #stablediffusion.
I chose stable diffusion.
PlaygroundAI: playgroundai.com
I chose stable diffusion.
PlaygroundAI: playgroundai.com
1. Text-based image editing is coming in hot!
Between #DALLE, #midjourney and #stablediffusion text-to-image generation is all the rage, but what if your images are off target?
Usually you try new prompts, then use inpainting to make edits... until now.
Between #DALLE, #midjourney and #stablediffusion text-to-image generation is all the rage, but what if your images are off target?
Usually you try new prompts, then use inpainting to make edits... until now.
2. This month multiple papers have come out demonstrating how language can be used to edit an image.
Equally exciting, these papers are being implemented on top of #stablediffusion since it's now openly available (Thanks @EMostaque!)
Let's review some of the ⚡️fast progress...
Equally exciting, these papers are being implemented on top of #stablediffusion since it's now openly available (Thanks @EMostaque!)
Let's review some of the ⚡️fast progress...
3. Last week, @FerranDeLaTorre and Chen Henry Wu released both a paper and code for CycleDiffusion.
CycleDiffusion allows existing text-to-image generation networks (e.g. #stablediffusion) to be used as text-guided image editors.
github.com/ChenWu98/cycle…
CycleDiffusion allows existing text-to-image generation networks (e.g. #stablediffusion) to be used as text-guided image editors.
github.com/ChenWu98/cycle…
Fun little #dalle hack: use in-painting to extend your brand.
Example: I created robots and patterns based on the Geppetto logo.
Example: I created robots and patterns based on the Geppetto logo.
For the robots, I was originally trying to come up with variations to see if it would improve. I kept portions of the logo and ran #dalle.
The result was a cute robot.
Realized I could rerun the prompt for infinite robot variations. Ta da!
The result was a cute robot.
Realized I could rerun the prompt for infinite robot variations. Ta da!
For the patterns, I first kept the head and then prompted #dalle for repeating patterns.
Took pieces of this new pattern and reran as a repeating pattern. Sometimes it didn’t work, as you can see.
Still, the result is a variety of pattern inspirations that match the branding!
Took pieces of this new pattern and reran as a repeating pattern. Sometimes it didn’t work, as you can see.
Still, the result is a variety of pattern inspirations that match the branding!
I built a No Code AI tool… w no code!
After building a few apps on top of #gpt3, realized I was missing toolsets, so built it myself.
It’s called Geppetto.
Here’s how it works 📖
After building a few apps on top of #gpt3, realized I was missing toolsets, so built it myself.
It’s called Geppetto.
Here’s how it works 📖
ICYMI, GPT-3 is a powerful AI tool where you provide it text, and it spits back text (poetry, code, etc).
It’s quite magical, but takes a bit to learn. Sometimes getting that initial text takes time. And if you get it right, you want to save the input text (called prompts).
It’s quite magical, but takes a bit to learn. Sometimes getting that initial text takes time. And if you get it right, you want to save the input text (called prompts).
Here’s an earlier deep dive I did into the space:
