正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Text-to-image after experiencing something like this? No way! I'll write a bit more about the setup in the🧵 #ai #art

Martin Nebelong

33,717 subscribers

381,474 次观看 • 2 年前 •via X (Twitter)

艺术科学技术 #ai #art

Anya Rossi• Live Now

Private livecam show

10 条评论

Martin Nebelong 的头像

Martin Nebelong2 年前

For this experiment, I used Krea AI, Photoshop, and my trusty old Cintiq 16". I used a small tool called "Peek Through" that allows you to make any window transparent. I used that on Photoshop so I could see the Krea AI website behind my drawing. In Krea, I set up screen2image to feed my Photoshop drawing into Krea in real-time. I was able to align both the transparent Photoshop window and Krea almost perfectly, so I got real-time feedback from drawing in Photoshop. So not exactly the most elegant workflow atm, but it's not too difficult to imagine something like this but in @midjourney or built directly into Photoshop with Firefly.

Doug McNabb 的头像

Doug McNabb2 年前

caveat: i've only used ChatGPT a few times now. is amazing how well it creates an image from text. but then it falls apart (for me, so far). "editing" is like wearing boxing gloves, under water, in the dark

Martin Nebelong 的头像

Martin Nebelong2 年前

Haha, that's a good way to describe it. "No, not like that, make it an s-shape.. no that's not it either, more rounded! No.. try to make the s-shape a big larger and more pronounced! AAARRRRgggghh" - Picks up a pen and draws a line over the image - "Like this.."

KREA AI 的头像

KREA AI2 年前

you're insane

Dan Shipper 📧 的头像

Dan Shipper 📧2 年前

hey! I run a podcast where I talk to people about how they use AI in their work. latest episode below. any interest in coming on?

ammyfatxolotl.bsky.social 的头像

ammyfatxolotl.bsky.social2 年前

keep lying to yourself

TAPgiles 的头像

TAPgiles2 年前

Oh wow, this is pretty compelling! And you can really see how real-time it is too.

Martin Nebelong 的头像

Martin Nebelong2 年前

It feels pretty amazing compared to text to image where I feel like I'm never really getting what I imagined. The missing human element is they key imo :D

Jason Staats⚡ 的头像

Jason Staats⚡2 年前

Martin when do we get the bob ross show for ai art

Martin Nebelong 的头像

Martin Nebelong2 年前

Hm.. I did it with Dreams, might be about time to do an AI version 🤔

相关视频

MatrixGPT - The state-of-the-art Text to Image AI app 💎An all-in-one #AI solution offering a suite of innovative apps including Text-to-image, Image-to-image, Text-to-speech & Talking face. Let's create art and earn with #MatrixGPT! JOIN US NOW!👉 $MAI

MatrixGPT - The state-of-the-art Text to Image AI app 💎An all-in-one #AI solution offering a suite of innovative apps including Text-to-image, Image-to-image, Text-to-speech & Talking face. Let's create art and earn with #MatrixGPT! JOIN US NOW!👉 $MAI

MatrixGPT

13,519 次观看 • 3 年前

My photoshop is more fun than yours 😜 With a bit of help from Krea ai. It's a crazy feeling to see brushstrokes transformed like this in realtime.. And the feeling of control is magnitudes better than with text prompts. #ai #art

My photoshop is more fun than yours 😜 With a bit of help from Krea ai. It's a crazy feeling to see brushstrokes transformed like this in realtime.. And the feeling of control is magnitudes better than with text prompts. #ai #art

Martin Nebelong

213,806 次观看 • 2 年前

Doing something a bit different. Whoever makes the best banner image for UploadThing gets $500 (+ I'll donate $500 more to a charity of their choice)

Doing something a bit different. Whoever makes the best banner image for UploadThing gets $500 (+ I'll donate $500 more to a charity of their choice)

Theo - t3.gg

174,970 次观看 • 2 年前

Took another stab at the water caustics shader after getting all that great feedback 🌊 Once this is refined a bit more I'll make sure to post the node setup 👍

Took another stab at the water caustics shader after getting all that great feedback 🌊 Once this is refined a bit more I'll make sure to post the node setup 👍

FrogmanDev

32,747 次观看 • 1 年前

UPDATE : I figured out what's making twitter flag my art as AI! it's the last image in the set, which is a real photo of a -blank- page with the artwork photoshopped onto it. it must be reading the text in it or something like that, that image makes the whole post get flagged.

UPDATE : I figured out what's making twitter flag my art as AI! it's the last image in the set, which is a real photo of a -blank- page with the artwork photoshopped onto it. it must be reading the text in it or something like that, that image makes the whole post get flagged.

✂️ Fold Up Toys ✂️

11,512 次观看 • 2 个月前

so, i'm controlling the stroke here, if this was longer and a bit more refined and i drew some complex art with something like this, would that be "ai slop", "stolen", etc.?

so, i'm controlling the stroke here, if this was longer and a bit more refined and i drew some complex art with something like this, would that be "ai slop", "stolen", etc.?

Utah teapot 🫖

80,587 次观看 • 5 个月前

Triggering text animation properties with bezier curves in After Effects opens up a playful way to manipulate text. In this setup, the only keyframes are for animating the path itself, while the path's length drives everything else. #AfterEffects #Animation #MotionDesign

Triggering text animation properties with bezier curves in After Effects opens up a playful way to manipulate text. In this setup, the only keyframes are for animating the path itself, while the path's length drives everything else. #AfterEffects #Animation #MotionDesign

François Lefebvre

23,281 次观看 • 2 年前

Using the new WordPress Command Palette to call an assistant that adds LLM generated text to a 3D world using natural language commands! "add text: write a short poem about the metaverse" This extends to image, audio and 3D objects in the future. WebXR holodeck style editing!

Using the new WordPress Command Palette to call an assistant that adds LLM generated text to a 3D world using natural language commands! "add text: write a short poem about the metaverse" This extends to image, audio and 3D objects in the future. WebXR holodeck style editing!

XR Publisher

17,891 次观看 • 2 年前

A 19-euro tool just replaced 8,000 Meta employees. Here’s the exact workflow a TikTok creator used to build AI influencer videos from scratch — no camera, no team, no budget. Step 1. Open Pinterest. Search “Girl Self.” Save the image you like. Open Nanobanana Pro. Step 2. Swap the face using a single prompt. (Link at the bottom.) Step 3. Take your generated photo into Crust. Currently the easiest video-from-image tool on the market. Step 4. Create 3 nodes: reference image, text, video generator. Step 5. Drop your photo into the image node. Write a video prompt into the text field. This is what makes the photo move. Step 6. Connect the nodes. Text to text-in. Image to image-in. Select Kling 2.6. Set duration. Toggle sound. Step 7. Hit generate. 2 prompts. 1 AI girl. 0 employees. Meta spent $14B on Reality Labs last year to build digital humans. This creator built one in 7 minutes for less than a dinner. The prompts are free in the reply.

A 19-euro tool just replaced 8,000 Meta employees. Here’s the exact workflow a TikTok creator used to build AI influencer videos from scratch — no camera, no team, no budget. Step 1. Open Pinterest. Search “Girl Self.” Save the image you like. Open Nanobanana Pro. Step 2. Swap the face using a single prompt. (Link at the bottom.) Step 3. Take your generated photo into Crust. Currently the easiest video-from-image tool on the market. Step 4. Create 3 nodes: reference image, text, video generator. Step 5. Drop your photo into the image node. Write a video prompt into the text field. This is what makes the photo move. Step 6. Connect the nodes. Text to text-in. Image to image-in. Select Kling 2.6. Set duration. Toggle sound. Step 7. Hit generate. 2 prompts. 1 AI girl. 0 employees. Meta spent $14B on Reality Labs last year to build digital humans. This creator built one in 7 minutes for less than a dinner. The prompts are free in the reply.

RGK🌹

185,627 次观看 • 1 个月前

I see your text prompt and raise you my 3d to anything.. It's all about control if we want Gen ai to be a useful creative tool. Keep reading to see the finished images based on this technique.🧵 #ai #art

I see your text prompt and raise you my 3d to anything.. It's all about control if we want Gen ai to be a useful creative tool. Keep reading to see the finished images based on this technique.🧵 #ai #art

Martin Nebelong

128,979 次观看 • 2 年前

Stayed up late until 2am yesterday to write a simple video cropping app because macOS surprisingly doesn't provide a quick way to do that. Anyone else needs something like this? If yes, I'll polish it a bit and put it as a free app in Mac App Store

Stayed up late until 2am yesterday to write a simple video cropping app because macOS surprisingly doesn't provide a quick way to do that. Anyone else needs something like this? If yes, I'll polish it a bit and put it as a free app in Mac App Store

An Tran

187,630 次观看 • 2 年前

Summer Bronya I was editing this model when I thought about making an image like this, but in the process I decided to make it animated. I also tried a new way of doing physics for hair/clothes I couldn't add something animated for the background, sorry I'll try to practice

Sensitive content

Summer Bronya I was editing this model when I thought about making an image like this, but in the process I decided to make it animated. I also tried a new way of doing physics for hair/clothes I couldn't add something animated for the background, sorry I'll try to practice

M K.

31,611 次观看 • 1 年前

This cinematic AI video started from a single image. No shoot. No camera setup. No editing timeline. Just Magnific + Seedance 2.0. And honestly… this feels like a glimpse into the future of creative workflows 👇

This cinematic AI video started from a single image. No shoot. No camera setup. No editing timeline. Just Magnific + Seedance 2.0. And honestly… this feels like a glimpse into the future of creative workflows 👇

Md Riyazuddin

15,012 次观看 • 1 个月前

Make a few more of these ... Make a LOT more of these ... Gemini 2.0 native image output is enabling a new way to prompt: instructing with image and text together. Subtle shifts in how I draw change how Gemini interprets the same text prompt.

Make a few more of these ... Make a LOT more of these ... Gemini 2.0 native image output is enabling a new way to prompt: instructing with image and text together. Subtle shifts in how I draw change how Gemini interprets the same text prompt.

Alexander Chen

23,601 次观看 • 1 年前

Ideogram AI presents Ideogram 1.0 text-to-image model offers state-of-the-art text rendering, unprecedented photorealism, exceptional prompt adherence, and a new feature called Magic Prompt to help with prompting

Ideogram AI presents Ideogram 1.0 text-to-image model offers state-of-the-art text rendering, unprecedented photorealism, exceptional prompt adherence, and a new feature called Magic Prompt to help with prompting

AK

96,079 次观看 • 2 年前

We’re making it much easier to attach files in Todoist, and we’re adding AI to the experience as well. One example is Image Scan, which can analyze an image, such as handwritten notes or a whiteboard, and turn it into actionable tasks. It’s a bit like Ramble, but for images. We’ll have something similar for text, too! Leak time 😄

We’re making it much easier to attach files in Todoist, and we’re adding AI to the experience as well. One example is Image Scan, which can analyze an image, such as handwritten notes or a whiteboard, and turn it into actionable tasks. It’s a bit like Ramble, but for images. We’ll have something similar for text, too! Leak time 😄

Amir Salihefendić

18,156 次观看 • 4 个月前

Something I didn't know Luma's new v1.5 was capable of: Knockout text effect! 🔴Let me know in the replies if you'd like the prompts for this text-to-video AI effect. Follow me for more experiments and prompts. #LumaDreamMachine

Something I didn't know Luma's new v1.5 was capable of: Knockout text effect! 🔴Let me know in the replies if you'd like the prompts for this text-to-video AI effect. Follow me for more experiments and prompts. #LumaDreamMachine

Christopher Fryant

20,451 次观看 • 1 年前

The people building AI are starting to ask questions about God. The tech industry may be experiencing a spiritual awakening. Follow this account for more

The people building AI are starting to ask questions about God. The tech industry may be experiencing a spiritual awakening. Follow this account for more

Steve Shultz

3,803,390 次观看 • 18 天前

There is something so miraculous about this. It took me a bit to realize there was NO INSTRUMENTS in the background. The way your voices just fill in the space makes it sound so full!! So many kudos 💗

There is something so miraculous about this. It took me a bit to realize there was NO INSTRUMENTS in the background. The way your voices just fill in the space makes it sound so full!! So many kudos 💗

🎼🌺Music Love♥️

14,065 次观看 • 9 个月前

stage director: for this segment's intro, how about something like a laser show. just a bit of it to liven it up lighting director: say no more

stage director: for this segment's intro, how about something like a laser show. just a bit of it to liven it up lighting director: say no more

mint

18,925 次观看 • 3 个月前