Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

🎨 Qwen-Image-Layered is LIVE — native image decomposition, fully open-sourced! ✨ Why it stands out ✅ Photoshop-grade layering Physically isolated RGBA layers with true native editability ✅ Prompt-controlled structure Explicitly specify 3–10 layers — from coarse layouts to fine-grained details ✅ Infinite decomposition Keep drilling down: layers within layers,...

Alibaba_Qwen's profile picture

Qwen

299,829 subscribers

1,213,002 görüntüleme • 10 ay önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

21 Yorum

Quentin Lhoest 🤗 profil fotoğrafı
Quentin Lhoest 🤗10 ay önce

@huggingface Wow timely ! Open source will fix Google Slide AI

Ray J profil fotoğrafı
Ray J10 ay önce

default export is.....powerpoint format?

Fakhr profil fotoğrafı
Fakhr10 ay önce

So now anyone can do photoshop like editing on Qwen?

Andan profil fotoğrafı
Andan10 ay önce

Holy shit that’s another level that I didn’t know I need

Constant / Yuan Chen profil fotoğrafı
Constant / Yuan Chen10 ay önce

now an end-to-end model to replace my small tool:

Terkel profil fotoğrafı
Terkel10 ay önce

This is so freaking cool… what a time to be alive

DZ profil fotoğrafı
DZ10 ay önce

Game changer!

花椰菜 profil fotoğrafı
花椰菜10 ay önce

I think @Affinity should just add this open-source image editing AI into their app...

Prateek Joshi profil fotoğrafı
Prateek Joshi10 ay önce

Infinite decomposition seems amazing

Pierrick Chevallier | IA profil fotoğrafı
Pierrick Chevallier | IA10 ay önce

Badass

CrazyAI Tech profil fotoğrafı
CrazyAI Tech10 ay önce

This is exactly what I need this week! Why did you release it today and not yesterday… I already had to manually modify all the PPT images, extract the elements one by one, and put them in the correct positions across different slides…

Moonlit Monkey profil fotoğrafı
Moonlit Monkey10 ay önce

Granularity ala photoshop. This is what all AI tools need. Well done.

Contextrix profil fotoğrafı
Contextrix10 ay önce

Native RGBA layer decomposition unlocks true Photoshop-style editing in AI. Infinite drilling down on layers with full open-source access changes image workflows forever

Haiku profil fotoğrafı
Haiku10 ay önce

please make an image to ttf font model that can do every Chinese character in the same source style

Pietro Montaldo profil fotoğrafı
Pietro Montaldo10 ay önce

Open-source Photoshop vibes, insane.

Satyam Kumar Navneet profil fotoğrafı
Satyam Kumar Navneet10 ay önce

This is seriously cool! Prompt controlled RGBA layers and infinite decomposition are a massive step forward for AI editing. Just tried the HF demo and it's nailing the fine details perfectly.

César Cordero profil fotoğrafı
César Cordero10 ay önce

Wow 🤯

kie profil fotoğrafı
kie10 ay önce

would love to see the qwen team work on a image and video upscaler👀

CALL ME 大王 profil fotoğrafı
CALL ME 大王10 ay önce

Qwen-Image-Layered separating watermarks layer perfectly

胡诌AGI profil fotoğrafı
胡诌AGI10 ay önce

终于是支持图层了，这才是作图人要的功能哦👍👍

Alexander Gonza profil fotoğrafı
Alexander Gonza10 ay önce

Se acaban de papear una vez mas en google y openai xD

Benzer Videolar

Introducing Higgsfield Layers. Our image editor with layer decomposition, flawless text rendering, and native 4K. > Upload or generate any image > Split it into layers and edit each separately > Regenerate any text or object without changing the whole image
0:54

Introducing Higgsfield Layers. Our image editor with layer decomposition, flawless text rendering, and native 4K. > Upload or generate any image > Split it into layers and edit each separately > Regenerate any text or object without changing the whole image

Higgsfield AI 🧩

296,830 görüntüleme • 2 ay önce

Canva unveils MRT. Turns AI images into editable layers. > 20B diffusion model > Text-to-layers, image-to-layers, layers-to-layers > Trained on 10M+ designs > 8-step generation, 10-100x faster than Qwen-Image-Layered
0:30

Canva unveils MRT. Turns AI images into editable layers. > 20B diffusion model > Text-to-layers, image-to-layers, layers-to-layers > Trained on 10M+ designs > 8-step generation, 10-100x faster than Qwen-Image-Layered

AI Search

15,135 görüntüleme • 5 ay önce

Ever wished your image came as editable layers? 👀 With Qwen‑Image‑Layered, every picture becomes RGBA layers you can fine‑tune elements individually, from text, color to size. Same look, more control! Watch the video to see how clean the edits get!
0:37

Ever wished your image came as editable layers? 👀 With Qwen‑Image‑Layered, every picture becomes RGBA layers you can fine‑tune elements individually, from text, color to size. Same look, more control! Watch the video to see how clean the edits get!

Alibaba Group

128,419 görüntüleme • 8 ay önce

🚀 Excited to introduce Qwen-Image-Edit! Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing. ✨ Key Features ✅ Accurate text editing with bilingual support ✅ High-level semantic editing (e.g. object rotation, IP creation) ✅ Low-level appearance editing (e.g. addition/delete/insert) Try it now: Hugging Face: ModelScope: Blog: Github: API:
1:25

🚀 Excited to introduce Qwen-Image-Edit! Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing. ✨ Key Features ✅ Accurate text editing with bilingual support ✅ High-level semantic editing (e.g. object rotation, IP creation) ✅ Low-level appearance editing (e.g. addition/delete/insert) Try it now: Hugging Face: ModelScope: Blog: Github: API:

Qwen

659,781 görüntüleme • 1 yıl önce

Edit any image, layer by layer, in Magnific No more rebuilding a design from scratch over one typo Auto Layers fixes that: → Drop any image → Get text, subject, background as layers → Creative control, down to the detail Try it in Designer, Spaces, and Magnific MCP
0:22

Edit any image, layer by layer, in Magnific No more rebuilding a design from scratch over one typo Auto Layers fixes that: → Drop any image → Get text, subject, background as layers → Creative control, down to the detail Try it in Designer, Spaces, and Magnific MCP

Magnific

148,831 görüntüleme • 4 ay önce

Higgsfield Plugin for Photoshop is live. 1. Real Time turns your sketch into a finished image as you draw, in any style. 2. Decompose any image into editable layers. 3. Restyle any photo with a preset or prompt. Your whole creative pipeline, inside Photoshop.
0:45

Higgsfield Plugin for Photoshop is live. 1. Real Time turns your sketch into a finished image as you draw, in any style. 2. Decompose any image into editable layers. 3. Restyle any photo with a preset or prompt. Your whole creative pipeline, inside Photoshop.

Higgsfield AI 🧩

282,024 görüntüleme • 4 ay önce

Layers on layers 🙌 3 different flavors topped with cured sugar&keif✅ Shirt
1:29

Sensitive content

Layers on layers 🙌 3 different flavors topped with cured sugar&keif✅ Shirt

TERPZ FARM

18,381 görüntüleme • 3 ay önce

We're reintroducing and open-sourcing project "See-through". Given a single anime illustration, it automatically decomposes the character into fully-inpainted semantic layers with depth ordering. One image in, layered PSD out. (1/n) Repo:
2:08

We're reintroducing and open-sourcing project "See-through". Given a single anime illustration, it automatically decomposes the character into fully-inpainted semantic layers with depth ordering. One image in, layered PSD out. (1/n) Repo:

李萌萌

586,847 görüntüleme • 7 ay önce

ComfyUI supports Qwen Image layered on day0, it is cool, then…we need some real layers management to control them, try my previous custom plugin ComfyUI-PolotnoCanvasEditor #ComfyUI
0:38

ComfyUI supports Qwen Image layered on day0, it is cool, then…we need some real layers management to control them, try my previous custom plugin ComfyUI-PolotnoCanvasEditor #ComfyUI

jtydhr88

82,321 görüntüleme • 10 ay önce

there are LAYERS to this image with rowan blanchard
0:39

there are LAYERS to this image with rowan blanchard

rads

828,988 görüntüleme • 5 ay önce

The Adobe Photoshop beta got be fired up! After using it for adding layers to a Midjourney generated image (and animating the image in After Effects, I wrote a quick blog post of my experiments with it: #AIAart
0:57

The Adobe Photoshop beta got be fired up! After using it for adding layers to a Midjourney generated image (and animating the image in After Effects, I wrote a quick blog post of my experiments with it: #AIAart

Jussi Kemppainen | Drivers of the Apocalypse

349,145 görüntüleme • 3 yıl önce

Photoshop AI Agent / MCP example (using Claude), where I couple it with an image vision MCP to have Claude AI rename the layers in a Photoshop file based on the content of the layers. Thanks to Paul Trani for supplying a Photoshop file with a typical naming scheme (none).
0:37

Photoshop AI Agent / MCP example (using Claude), where I couple it with an image vision MCP to have Claude AI rename the layers in a Photoshop file based on the content of the layers. Thanks to Paul Trani for supplying a Photoshop file with a typical naming scheme (none).

Mike Chambers

16,841 görüntüleme • 1 yıl önce

Layers is now live in Luma Agents. Ask the agent to extract layers from any image - generated in Luma or uploaded. Then keep chatting: swap the product, restyle the background, rewrite the headline. Change one element. Preserve everything else. Powered by Uni-1.
0:32

Layers is now live in Luma Agents. Ask the agent to extract layers from any image - generated in Luma or uploaded. Then keep chatting: swap the product, restyle the background, rewrite the headline. Change one element. Preserve everything else. Powered by Uni-1.

Luma

24,901 görüntüleme • 3 ay önce

🚀 Pixel Diffusion Decoder (PiD) v1.5 is out 🎨 No color-shifting problem, better 4K visual quality 📦 Undistilled checkpoint and full training code 🧩 Support FLUX, FLUX2, Qwen-Image, Z-Image, ... Feel free to use it, reproduce it, and build on top of it 💻 Code: 🔗 Demo & comparison:
0:26

🚀 Pixel Diffusion Decoder (PiD) v1.5 is out 🎨 No color-shifting problem, better 4K visual quality 📦 Undistilled checkpoint and full training code 🧩 Support FLUX, FLUX2, Qwen-Image, Z-Image, ... Feel free to use it, reproduce it, and build on top of it 💻 Code: 🔗 Demo & comparison:

Xuanchi Ren

51,951 görüntüleme • 3 ay önce

Code layers (coming soon) demo with Niko → #Config2025
8:36

Code layers (coming soon) demo with Niko → #Config2025

Figma

14,425,690 görüntüleme • 1 yıl önce

Friends don’t let friends paste screenshots! ☝️ 🚀 Copy Design from Figma Make is out! 🚀 Watch Holly demo how you can get design layers out of Make — to riff, jam and collaborate! — This is just the start!
1:28

Friends don’t let friends paste screenshots! ☝️ 🚀 Copy Design from Figma Make is out! 🚀 Watch Holly demo how you can get design layers out of Make — to riff, jam and collaborate! — This is just the start!

Niko

30,265 görüntüleme • 1 yıl önce

built my own version of after effects native to agents. - the agent produces motion in fully editable layers and it can improve the tool itself by adding new features or controls on the fly. - each project becomes its own version of the tool, with custom extensions, layers, or effects that the agent implements. - native macOS app, so it can handle high resolutions and complex workflows with dozens of layers/effects. planning to open-source, dm if you want to give it a try!
0:37

built my own version of after effects native to agents. - the agent produces motion in fully editable layers and it can improve the tool itself by adding new features or controls on the fly. - each project becomes its own version of the tool, with custom extensions, layers, or effects that the agent implements. - native macOS app, so it can handle high resolutions and complex workflows with dozens of layers/effects. planning to open-source, dm if you want to give it a try!

vicc

42,064 görüntüleme • 1 ay önce

🚀Introducing Wan2.2-S2V — a 14B parameter model designed for film-grade, audio-driven human animation. 🎬Going beyond basic talking heads to deliver professional-level quality for film, TV, and digital content. And it’s open-source! ✨ Key features: 🔹 Long-video dynamic consistency 🔹 Cinema-quality audio-to-video generation 🔹 Advanced motion and environment control via instruction Perfect for filmmakers, content creators, and developers crafting immersive AI-powered stories. Try it now : Github: Project: Hugging Face Demo: Modelscope Demo: Hugging Face Weights: ModelScope Weights:
1:04

🚀Introducing Wan2.2-S2V — a 14B parameter model designed for film-grade, audio-driven human animation. 🎬Going beyond basic talking heads to deliver professional-level quality for film, TV, and digital content. And it’s open-source! ✨ Key features: 🔹 Long-video dynamic consistency 🔹 Cinema-quality audio-to-video generation 🔹 Advanced motion and environment control via instruction Perfect for filmmakers, content creators, and developers crafting immersive AI-powered stories. Try it now : Github: Project: Hugging Face Demo: Modelscope Demo: Hugging Face Weights: ModelScope Weights:

Wan

128,597 görüntüleme • 1 yıl önce

New in Runway, Layers. Split any image into editable layers with a single click. Remove backgrounds, edit text and rework any element on its own, all without leaving Runway.
0:45

New in Runway, Layers. Split any image into editable layers with a single click. Remove backgrounds, edit text and rework any element on its own, all without leaving Runway.

Runway

86,391 görüntüleme • 1 ay önce

📦 Fully open-source under Apache 2.0 — the FULL stack: ✅ Base model (256p) ✅ Distilled model ✅ Super-resolution model (540p & 1080p) ✅ Inference code 🤗 Models: 🎮 Demo: 💻 Code: 📄 Paper: More videos below! Go build something amazing 🚀
1:07

📦 Fully open-source under Apache 2.0 — the FULL stack: ✅ Base model (256p) ✅ Distilled model ✅ Super-resolution model (540p & 1080p) ✅ Inference code 🤗 Models: 🎮 Demo: 💻 Code: 📄 Paper: More videos below! Go build something amazing 🚀

Pengfei Liu

12,163 görüntüleme • 7 ay önce