Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

generative editing timelapse with Krea editor adding a pool, chimney, clouds, expanding image, moving house & trees

titus

3,047 subscribers

309,582 görüntüleme • 1 yıl önce •via X (Twitter)

Sanat Eğitim Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

11 Yorum

pedro lucca profil fotoğrafı

pedro lucca1 yıl önce

@krea_ai when I was a teen I'd join "photomanipulations" contests on youtube we'd spend hours doing crazy shit manually on photoshop - this feels like a childhood dream come true

UserInterface profil fotoğrafı

UserInterface4 yıl önce

Need Professional Video Production, Music Videos, Commercials, Graphic Design, or Photo Retouching? We will take your project from concept to completion. #services #creative #DMV

Senses.AI profil fotoğrafı

Senses.AI1 yıl önce

@krea_ai Architectural assets are grossly underestimated for generative AI, Well done!

Senses.AI profil fotoğrafı

Senses.AI1 yıl önce

@krea_ai Allowing to bring and upload own pictures to improve a home improvement or home design would be a homerun!

titus profil fotoğrafı

titus1 yıl önce

@krea_ai oh, edit already works with uploaded images. you can just take a photo on your phone and edit it in krea

Riley Brown profil fotoğrafı

Riley Brown1 yıl önce

@krea_ai does it work with an image upload?

Mac Baconai profil fotoğrafı

Mac Baconai1 yıl önce

@krea_ai 🧡

kie profil fotoğrafı

kie1 yıl önce

@krea_ai its so good

Florian profil fotoğrafı

Florian1 yıl önce

@krea_ai Love this!

Marcel Ohrenschall ⚡️ profil fotoğrafı

Marcel Ohrenschall ⚡️1 yıl önce

@krea_ai An issue I regulary have with midjourneys editor is that the output for altered areas looks artifical, lights and shapes are often misplaced, in photoshop that's even worse. This problem looks like perfectly mastered here with krea.

Attick profil fotoğrafı

Attick1 yıl önce

@krea_ai what the hell, this is sick af

Benzer Videolar

Image Editor is now live in FLORA. Composite, inpaint, outpaint, resize, split into layers. It’s a complete editing environment inside your generative workflow. Finish your ideas in FLORA.

Image Editor is now live in FLORA. Composite, inpaint, outpaint, resize, split into layers. It’s a complete editing environment inside your generative workflow. Finish your ideas in FLORA.

FLORA ©

49,040 görüntüleme • 7 ay önce

This started as just one image… then I turned it into a cinematic video with AI. I tested “Video AI” to see how much life I could bring to a single static image → Upload the image → choose your settings → generate. No timeline. No complicated editing. No manual animation. Just one image transformed into a moving, cinematic scene.🧵

This started as just one image… then I turned it into a cinematic video with AI. I tested “Video AI” to see how much life I could bring to a single static image → Upload the image → choose your settings → generate. No timeline. No complicated editing. No manual animation. Just one image transformed into a moving, cinematic scene.🧵

Aryan Rakib

104,969 görüntüleme • 20 gün önce

Today, history has been made. Veo 3 image-to-video is now here – a landmark moment in the history of moving image art. Just like film was revolutionized by the introduction of sound, generative AI has made leaps with this groundbreaking model. Try it for yourself in FLORA.

Today, history has been made. Veo 3 image-to-video is now here – a landmark moment in the history of moving image art. Just like film was revolutionized by the introduction of sound, generative AI has made leaps with this groundbreaking model. Try it for yourself in FLORA.

FLORA ©

16,616 görüntüleme • 1 yıl önce

Rosii says Arky is moving to Austin to start a streamer house with him & Zoil 😮

Rosii says Arky is moving to Austin to start a streamer house with him & Zoil 😮

Cinna Updates

25,776 görüntüleme • 3 ay önce

Tencent presents TIP-Editor An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts paper page: Text-driven 3D scene editing has gained significant attention owing to its convenience and user-friendliness. However, existing methods still lack accurate control of the specified appearance and location of the editing result due to the inherent limitations of the text description. To this end, we propose a 3D scene editing framework, TIPEditor, that accepts both text and image prompts and a 3D bounding box to specify the editing region. With the image prompt, users can conveniently specify the detailed appearance/style of the target content in complement to the text description, enabling accurate control of the appearance. Specifically, TIP-Editor employs a stepwise 2D personalization strategy to better learn the representation of the existing scene and the reference image, in which a localization loss is proposed to encourage correct object placement as specified by the bounding box. Additionally, TIPEditor utilizes explicit and flexible 3D Gaussian splatting as the 3D representation to facilitate local editing while keeping the background unchanged. Extensive experiments have demonstrated that TIP-Editor conducts accurate editing following the text and image prompts in the specified bounding box region, consistently outperforming the baselines in editing quality, and the alignment to the prompts, qualitatively and quantitatively.

Tencent presents TIP-Editor An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts paper page: Text-driven 3D scene editing has gained significant attention owing to its convenience and user-friendliness. However, existing methods still lack accurate control of the specified appearance and location of the editing result due to the inherent limitations of the text description. To this end, we propose a 3D scene editing framework, TIPEditor, that accepts both text and image prompts and a 3D bounding box to specify the editing region. With the image prompt, users can conveniently specify the detailed appearance/style of the target content in complement to the text description, enabling accurate control of the appearance. Specifically, TIP-Editor employs a stepwise 2D personalization strategy to better learn the representation of the existing scene and the reference image, in which a localization loss is proposed to encourage correct object placement as specified by the bounding box. Additionally, TIPEditor utilizes explicit and flexible 3D Gaussian splatting as the 3D representation to facilitate local editing while keeping the background unchanged. Extensive experiments have demonstrated that TIP-Editor conducts accurate editing following the text and image prompts in the specified bounding box region, consistently outperforming the baselines in editing quality, and the alignment to the prompts, qualitatively and quantitatively.

AK

56,428 görüntüleme • 2 yıl önce

Lacy revealed that he, StableRonaldo, Silky, & Marlon toured a perfect house for the group and are hoping to get accepted since they’re moving out of the ex FaZe house soon 👀🔥 - Huge yard - Pool - Full Basketball Court

Lacy revealed that he, StableRonaldo, Silky, & Marlon toured a perfect house for the group and are hoping to get accepted since they’re moving out of the ex FaZe house soon 👀🔥 - Huge yard - Pool - Full Basketball Court

Salt 💫

170,557 görüntüleme • 8 ay önce

The Trump Administration is adding rocket fuel to America’s space economy. Finishing up a great visit to Midland, TX with Chairman Senator Ted Cruz where we toured a high-tech satellite manufacturing plant that’s been adding jobs & expanding production. Great for the country! 🇺🇸

The Trump Administration is adding rocket fuel to America’s space economy. Finishing up a great visit to Midland, TX with Chairman Senator Ted Cruz where we toured a high-tech satellite manufacturing plant that’s been adding jobs & expanding production. Great for the country! 🇺🇸

Brendan Carr

328,377 görüntüleme • 1 yıl önce

Need a video editor? Your wish is my command 🫣 Experience in retention editing and clean motion graphics for 5+ years 🚶‍♂️⬆️ DM ME 📩 worked with & Codie Sanchez ♻️& ♥️ are greatly appreciated

Need a video editor? Your wish is my command 🫣 Experience in retention editing and clean motion graphics for 5+ years 🚶‍♂️⬆️ DM ME 📩 worked with & Codie Sanchez ♻️& ♥️ are greatly appreciated

maison

16,003 görüntüleme • 3 yıl önce

Lisa loved podcasting but hated spending hours turning her audio into videos. Editing was time-consuming. Syncing visuals, adding captions, and cutting clips-it felt endless. Then she found Wondershare Filmora Video Editor. With just a few clicks, AI transformed her podcast into polished videos. No manual editing, no wasted time. Here’s how Lisa did it - and you can too.

Lisa loved podcasting but hated spending hours turning her audio into videos. Editing was time-consuming. Syncing visuals, adding captions, and cutting clips-it felt endless. Then she found Wondershare Filmora Video Editor. With just a few clicks, AI transformed her podcast into polished videos. No manual editing, no wasted time. Here’s how Lisa did it - and you can too.

Chidanand Tripathi

52,752 görüntüleme • 1 yıl önce

1/ Introducing Playground with Mixed Image Editing. A new way to combine real and synthetic images to create stunning works of art & photorealistic images bound only by your imagination. Try now:

1/ Introducing Playground with Mixed Image Editing. A new way to combine real and synthetic images to create stunning works of art & photorealistic images bound only by your imagination. Try now:

Suhail

599,554 görüntüleme • 3 yıl önce

We gave four frontier image editing models the same photo and 30 edits in a row: Ideogram 4.5 keeps most of the room intact, while the others drift, GPT Image 2.5 Sunburst most visibly. We've seen some interesting demos of multi-turn editing consistency from the latest image editing models, so we ran our own test: GPT Image 2.5 Sunburst, #1 on our Image Editing leaderboard, against Ideogram 4.5, FLUX 3 and Nano Banana 2.1. Our leaderboard scores single edits; this tests what happens when 30 consecutive changes stack up, with each model editing its own previous output through a 30-step real estate staging sequence: light the fire, add a sofa, repaint the walls, swap day for twilight, and more. Why are the final results so different? Ideogram's Ideogram 4.5 and BlackForestLabsAI - Unofficial's FLUX 3 edit locally. On small edits like adding a vase of tulips, we measured that they left 95% or more of the image essentially untouched. GPT Image 2.5 (Sunburst) re-renders most of the entire image on every edit, leaving only about a fifth of the image unchanged, so small shifts in colour and detail compound over turns. Nano Banana 2.1 sits in between: its edits stay local, but the rest of the image shifts slightly and gradually darkens.

We gave four frontier image editing models the same photo and 30 edits in a row: Ideogram 4.5 keeps most of the room intact, while the others drift, GPT Image 2.5 Sunburst most visibly. We've seen some interesting demos of multi-turn editing consistency from the latest image editing models, so we ran our own test: GPT Image 2.5 Sunburst, #1 on our Image Editing leaderboard, against Ideogram 4.5, FLUX 3 and Nano Banana 2.1. Our leaderboard scores single edits; this tests what happens when 30 consecutive changes stack up, with each model editing its own previous output through a 30-step real estate staging sequence: light the fire, add a sofa, repaint the walls, swap day for twilight, and more. Why are the final results so different? Ideogram's Ideogram 4.5 and BlackForestLabsAI - Unofficial's FLUX 3 edit locally. On small edits like adding a vase of tulips, we measured that they left 95% or more of the image essentially untouched. GPT Image 2.5 (Sunburst) re-renders most of the entire image on every edit, leaving only about a fifth of the image unchanged, so small shifts in colour and detail compound over turns. Nano Banana 2.1 sits in between: its edits stay local, but the rest of the image shifts slightly and gradually darkens.

Artificial Analysis

88,915 görüntüleme • 10 gün önce

🚨Democrats moving towards adding a “Methane Tax” PER CATTLE. “This is the first step to imposing a per head methane tax on cattle, similar to what Denmark imposed this summer. The bill is currently with the committee in the house”

🚨Democrats moving towards adding a “Methane Tax” PER CATTLE. “This is the first step to imposing a per head methane tax on cattle, similar to what Denmark imposed this summer. The bill is currently with the committee in the house”

Derrick Evans

137,128 görüntüleme • 1 yıl önce

Someone has to find out if there’s money to be made trading on Robinhood Crypto I’m too lazy to look into it, so I guess Misato just got a job 🤣 —— Design frames with gpt-image-2.5, animation with seedance2.5. Generative AI is moving so fast I’m running out of words. What a time to be alive. #NOESIS Pons

Someone has to find out if there’s money to be made trading on Robinhood Crypto I’m too lazy to look into it, so I guess Misato just got a job 🤣 —— Design frames with gpt-image-2.5, animation with seedance2.5. Generative AI is moving so fast I’m running out of words. What a time to be alive. #NOESIS Pons

YeHe (🦾,🧠)

10,329 görüntüleme • 1 ay önce

The budget is a careful balance of efficiencies, cuts, and new revenue. On Monday, I introduced an ordinance expanding the downtown rideshare surcharge zone & adding weekends. This could bring: ✅ $10-15M in revenue ✅ Lower property taxes A small change with a big impact.

The budget is a careful balance of efficiencies, cuts, and new revenue. On Monday, I introduced an ordinance expanding the downtown rideshare surcharge zone & adding weekends. This could bring: ✅ $10-15M in revenue ✅ Lower property taxes A small change with a big impact.

Alderman Daniel La Spata

37,498 görüntüleme • 1 yıl önce

Added real-time color image transfer to the point cloud & tracking setup. Now you can sync device pose and spatial structure to a remote environment simultaneously. From Quest to mobile, the possibilities are expanding. What would you build with this? #MetaQuest3 #MixedReality

Added real-time color image transfer to the point cloud & tracking setup. Now you can sync device pose and spatial structure to a remote environment simultaneously. From Quest to mobile, the possibilities are expanding. What would you build with this? #MetaQuest3 #MixedReality

Takashi Yoshinaga

36,480 görüntüleme • 9 ay önce

Meet Donald Trump’s accuser E. Jean Carroll: She lives in a house with mice in the middle of the forest called “The Mouse House” Has bizarre names for her dogs Paints trees & rocks in the forest This woman is unstable and people treat her as “credible”

Meet Donald Trump’s accuser E. Jean Carroll: She lives in a house with mice in the middle of the forest called “The Mouse House” Has bizarre names for her dogs Paints trees & rocks in the forest This woman is unstable and people treat her as “credible”

Benny Johnson

2,656,381 görüntüleme • 2 yıl önce

Today, we introduce HunyuanImage 3.0-Instruct, a native multimodal model focusing on image-editing by integrating visual understanding with precise image synthesis! 🚀 It understands input images and reasons before generating images. Built on an 80B-parameter MoE architecture (13B activated), it natively unifies deep multimodal comprehension and high-fidelity generation. 🧠 A "Thinking" Model with Native CoT & MixGRPO: The model doesn’t just execute commands, it processes them through a Native Chain-of-Thought (CoT) schema. Enhanced by our self-developed MixGRPO algorithm, it reasons through complex instructions to achieve flawless intent alignment and human-preference consistency. 🎨 Precise Editing & Multi-Image Fusion: The model enables accurate image editing by adding, removing, or modifying elements while keeping non-target areas perfectly intact. It also excels at seamless multi-image fusion, synthesizing complex scenes by extracting and blending elements from multiple sources into a unified, consistent output. 🏆 SOTA Performance: HunyuanImage 3.0-Instruct sets a new benchmark in visual quality and alignment, delivering performance that matches leading proprietary models. We aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant image generation ecosystem. 🛠️🎨 💻Try it at (PC only):

Today, we introduce HunyuanImage 3.0-Instruct, a native multimodal model focusing on image-editing by integrating visual understanding with precise image synthesis! 🚀 It understands input images and reasons before generating images. Built on an 80B-parameter MoE architecture (13B activated), it natively unifies deep multimodal comprehension and high-fidelity generation. 🧠 A "Thinking" Model with Native CoT & MixGRPO: The model doesn’t just execute commands, it processes them through a Native Chain-of-Thought (CoT) schema. Enhanced by our self-developed MixGRPO algorithm, it reasons through complex instructions to achieve flawless intent alignment and human-preference consistency. 🎨 Precise Editing & Multi-Image Fusion: The model enables accurate image editing by adding, removing, or modifying elements while keeping non-target areas perfectly intact. It also excels at seamless multi-image fusion, synthesizing complex scenes by extracting and blending elements from multiple sources into a unified, consistent output. 🏆 SOTA Performance: HunyuanImage 3.0-Instruct sets a new benchmark in visual quality and alignment, delivering performance that matches leading proprietary models. We aim to enable the community to explore new ideas with a state-of-the-art foundation model, fostering a dynamic and vibrant image generation ecosystem. 🛠️🎨 💻Try it at (PC only):

Tencent Hy

126,668 görüntüleme • 8 ay önce