Discover and read the best of Twitter Threads about #dreamstudio
Most recents (11)
What important messages would Jesus share if he found himself resurrected at Walmart?
#HappyEaster #JesusChrist #Church #Christianity #WorshipAI #HealthyLiving #Walmart #AIArtCommunity #MidJourney #MindJourney
🧵Thread - Share your thoughts on AI merging with religion and… twitter.com/i/web/status/1…
#HappyEaster #JesusChrist #Church #Christianity #WorshipAI #HealthyLiving #Walmart #AIArtCommunity #MidJourney #MindJourney
🧵Thread - Share your thoughts on AI merging with religion and… twitter.com/i/web/status/1…
Would he have anything to say about kosher food?
What would Jesus think about plastic Easter eggs?
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…
Un hack muy 🔝 para quienes se les atraganta el prompt de las #IA de generación de imágenes (el texto fuente de las que parte). Con este método se acabó quemar créditos haciendo pruebas con farragosos prompts hasta dar con un resultado atractivo ⬇️
Le he pedido a #ChatGPT (#IA de chat de texto) que me describa un dormitorio moderno y relajante, en inglés (usa aquí una herramienta de traducción como Google Translate, si es necesario). Me quedo solo con la parte descriptiva, el resto es literatura que no es útil.
Me lo llevo a mi #IA de generación de imágenes (#DreamStudio en mi caso) y lo pego, tal cual, en el prompt. Voilà!
1/10 kicking off our #octaneX news at yesterday’s #AppleEvent - I want to share a preview of a major topic I will cover in my @solana $rndr breakpoint talk in a few weeks:
2/10 On iPad and iPhone, millions of new artists will need to be onboarded to #rndr with a much simpler workflow than desktop 3D tools currently offer. With #RNDR baked into the design of our new app, we believe have a way to address this:
3/10 In March at #GTC22, I first previewed our Neural Rendering work: AI and raytracing seamlessly blend in a single GPU rendering pipeline: #RNDR twitter.com/i/web/status/1…
I'm working on a tool for #promptEngineer #aiart 👀
This will blow your mind, you'll be able to store prompts and generations from Dalle2, DreamStudio and MJ (from browser)
If you want early access, signup here:
myai.art
This will blow your mind, you'll be able to store prompts and generations from Dalle2, DreamStudio and MJ (from browser)
If you want early access, signup here:
myai.art
A brief breakdown of currently supported features:
⭐️ Select any text and generate it with SD1.5
(Could this be the reason Getty images stopped submissions of AiArt? 🤔)
⭐️ Select any text and generate it with SD1.5
(Could this be the reason Getty images stopped submissions of AiArt? 🤔)
🔥 Right click any image and use that as init_img for img2img generation.
Select how strong you'd like the init image to inspire your generation
Select how strong you'd like the init image to inspire your generation
Gather round my #aiArtists , and let me show you something:
This is called #stableDiffusion webui
Not to be confused with #dreamStudio, this runs on your machine/python and is even accessible remotely via ipad/iphone!
Features in 🧵 (you don't want to miss this)
This is called #stableDiffusion webui
Not to be confused with #dreamStudio, this runs on your machine/python and is even accessible remotely via ipad/iphone!
Features in 🧵 (you don't want to miss this)
It's Jam-packed with features, here are the mains ones:
✨ Use from your phone/ipad
✨ Built in upscaling with ESRGan / CFGGan (quality & face) so you get high-er quality results
✨ Comes with k_lms, k_euler and k_euler_a sampling methods, for low step <> high cohesion results
✨ Use from your phone/ipad
✨ Built in upscaling with ESRGan / CFGGan (quality & face) so you get high-er quality results
✨ Comes with k_lms, k_euler and k_euler_a sampling methods, for low step <> high cohesion results
✨ Create a prompt matrix
Testing several combinations of prompts and artists and styles, for example:
cartoon dog | by greg rutkowski | unity 3d | still frame from rick and morty
Will give you this matrix, and each one of the results individually.
Testing several combinations of prompts and artists and styles, for example:
cartoon dog | by greg rutkowski | unity 3d | still frame from rick and morty
Will give you this matrix, and each one of the results individually.
How To Use #DreamStudio #StableDiffusion To Create A Traditional Illustration.
(A micro micro micro documentary with an all-caps title to make it look impressive)
Let's start with the finished illustration (you'll want to zoom in on it, so click and read the small print):
1/🧵
(A micro micro micro documentary with an all-caps title to make it look impressive)
Let's start with the finished illustration (you'll want to zoom in on it, so click and read the small print):
1/🧵
After 1-2 hours of generating terrible concepts, I finally landed on the idea of a cat reading books on how do cat stuff, including manipulating humans. Fun! Started with maybe 30 "cats in chairs" renders in #stablediffusion to get ideas:
2/🧵
2/🧵
I liked the cat face in the first one, but would need to hand edit the body to add a book so we could see the title. Then I decided I wanted him on a couch, not chair, to make seeing his pile of books easier. But first I edited the prompt to give me library ideas:
3/🧵
3/🧵
Alfred Hitchcock serving tea to the MGM lion:
1) how its started (original real photo)
2) how it went in #stablediffusion
3) how it went in #dalle2
1) how its started (original real photo)
2) how it went in #stablediffusion
3) how it went in #dalle2
not fair on the #dalle image i choose for quality, but it got the composition right. here is a better render but not the right composition:
Delighted to announce the public open source release of #StableDiffusion!
Please see our release post and retweet! stability.ai/blog/stable-di…
Proud of everyone involved in releasing this tech that is the first of a series of models to activate the creative potential of humanity
Please see our release post and retweet! stability.ai/blog/stable-di…
Proud of everyone involved in releasing this tech that is the first of a series of models to activate the creative potential of humanity
We are also delighted to announce the public beta release of #DreamStudio, our reference implementation to allow anyone to create anything.
The public API will be available here shortly to extend your creativity and enable new experiences.
beta.dreamstudio.ai
The public API will be available here shortly to extend your creativity and enable new experiences.
beta.dreamstudio.ai
We have more to come and expect an explosion of originality in UI/UX and new ways to create both from our efforts and those of the community, which everyone should join at discord.gg/stablediffusion !
Developers, creatives and those inspired by this, all are welcome to come & dream
Developers, creatives and those inspired by this, all are welcome to come & dream
Some thoughts on #StableDiffusion vs #DALLE2 vs #midjourney
They are actually all different (complementary?).
First this whole field was catalysed by @OpenAI releasing CLIP publicly last year (!) which @RiversHaveWings, @advadnoun and others built on openai.com/blog/clip/
They are actually all different (complementary?).
First this whole field was catalysed by @OpenAI releasing CLIP publicly last year (!) which @RiversHaveWings, @advadnoun and others built on openai.com/blog/clip/
This allowed image generation to be guided, the output of which was surprising and led to a burst of developer and artist creativity from @ClaireSilver12 and many others.
Proud to say we supported & funded most of the open tools in this space.
It is now good enough, fast enough
Proud to say we supported & funded most of the open tools in this space.
It is now good enough, fast enough
So #dalle2 is a model and a service.
It is focused on a certain usage subset that will broaden.
Inpainting is it’s best feature but by default it is random and best used for ideation and more corporate usage, hence it’s clear training on licensed stock images
It is focused on a certain usage subset that will broaden.
Inpainting is it’s best feature but by default it is random and best used for ideation and more corporate usage, hence it’s clear training on licensed stock images
Como investigador especializado en la historia de las imágenes científicas estoy siguiendo con mucho interés la evolución de los programas de generación de imágenes por #InteligenciaArtificial.
En este HILO voy a ir recopilando algunas reflexiones sobre el tema 👇
En este HILO voy a ir recopilando algunas reflexiones sobre el tema 👇
Por cierto, la imagen de arriba NO está generada mediante #AI. Es un dibujo atribuido al artista Jacopo Ligozzi (1547-1627), perteneciente al @museodelprado
Pero creo que captura bien el elemento "quimérico" de esta nueva y fascinante cultural visual
🔗 museodelprado.es/coleccion/obra…
Pero creo que captura bien el elemento "quimérico" de esta nueva y fascinante cultural visual
🔗 museodelprado.es/coleccion/obra…
Cuestiones que me interesa explorar:
1⃣ El lenguaje. Al tratarse de programas “text to image”, el input textual es clave. Me interesa cómo estos programas responden al lenguaje que empleamos los historiadores a la hora de estudiar las imágenes y los temas que representan. *
1⃣ El lenguaje. Al tratarse de programas “text to image”, el input textual es clave. Me interesa cómo estos programas responden al lenguaje que empleamos los historiadores a la hora de estudiar las imágenes y los temas que representan. *
