Загрузка видео...

Не удалось загрузить видео

На главную

Canva launches Brush, a vision-language model built specifically for design editing. It restyles designs, adapts them to new formats, and applies consistent changes across multi-page designs. Craft, Canva’s first image model, debuted earlier this week at #4 on DesignArena’s leaderboard. In internal testing, Brush matched or exceeded the quality...

DocumentingAGI's profile picture

Documenting AGI

66,457 subscribers

16,942 просмотров • 6 дней назад •via X (Twitter)

Наука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 7

Фото профиля Weijie
Weijie4 дней назад

@DesignArena Craft 排第4 Brush 只管编辑? 跨页一致性谁兜

Фото профиля Riley L.
Riley L.6 дней назад

@DesignArena Version control becomes very tricky

Фото профиля Charlie T.
Charlie T.6 дней назад

@DesignArena Production stability is the real test

Фото профиля Nova C.
Nova C.6 дней назад

@DesignArena Routine design work may suffer

Фото профиля Asim
Asim6 дней назад

@DesignArena SO then it messes logos?

Фото профиля Günay Alkan
Günay Alkan6 дней назад

@DesignArena Most design tools require additional software to preserve editability after automated changes.

Фото профиля Kt
Kt6 дней назад

@DesignArena What extra do users need now

Похожие видео

Anyone who has used AI for design knows the struggle: the first draft looks great, then you ask for one small change and it redraws everything. That's what Canva built Brush for: it's their own vision-language model for design editing. It reads how the elements fit together and plans the changes before making them. Last week Canva released Craft, which makes the images. Now Brush, to handle everything after🌸
0:25

Anyone who has used AI for design knows the struggle: the first draft looks great, then you ask for one small change and it redraws everything. That's what Canva built Brush for: it's their own vision-language model for design editing. It reads how the elements fit together and plans the changes before making them. Last week Canva released Craft, which makes the images. Now Brush, to handle everything after🌸

karla

48,576 просмотров • 6 дней назад

Introducing Brush: Our first vision-language model for design. 🖌️ Brush sees your design’s layout, layers and vibe the way you do, and edits alongside you. Fix one line of text, restyle a whole deck or build from a blank page. See what Brush can do 👇
0:57

Introducing Brush: Our first vision-language model for design. 🖌️ Brush sees your design’s layout, layers and vibe the way you do, and edits alongside you. Fix one line of text, restyle a whole deck or build from a blank page. See what Brush can do 👇

Canva

2,622,589 просмотров • 6 дней назад

Introducing Canva Craft 🚀 Extraordinary image generation is now available to everyone, powered by our first frontier model built specifically for design. With Craft, Canva is now the world's second most advanced AI lab for image generation on DesignArena's global leaderboard. See what it can do 👇
0:35

Introducing Canva Craft 🚀 Extraordinary image generation is now available to everyone, powered by our first frontier model built specifically for design. With Craft, Canva is now the world's second most advanced AI lab for image generation on DesignArena's global leaderboard. See what it can do 👇

Canva

1,946,512 просмотров • 13 дней назад

At 4:30am this morning Lola dropped her brush and exceeded the 72 hours she set for herself She set a new record of 82 hours and some minutes before she dropped her brush #lolamewuspainthaton #lolamewuspaintingmarathon
0:33

At 4:30am this morning Lola dropped her brush and exceeded the 72 hours she set for herself She set a new record of 82 hours and some minutes before she dropped her brush #lolamewuspainthaton #lolamewuspaintingmarathon

Oyinlola 🍀

74,229 просмотров • 3 лет назад

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes. ByteDance's latest image model brings: → Character & product consistency across edits → Precision region editing → Infographics, flowcharts & structured layouts → In-image text across 14 languages One model. Text-to-image, editing, and multi-image inputs. Click the link below for the workflow 👇
0:32

Seedream 5.0 Pro is now in ComfyUI via Partner Nodes. ByteDance's latest image model brings: → Character & product consistency across edits → Precision region editing → Infographics, flowcharts & structured layouts → In-image text across 14 languages One model. Text-to-image, editing, and multi-image inputs. Click the link below for the workflow 👇

ComfyUI

14,756 просмотров • 3 месяцев назад

Opus 4.5 (new model from Anthropic) can do something no model could do until now: It can close the design loop. This is (in my testing) the first model that can reliably do the visual loop of Generate Code ⇛ Render ⇛ Look at it ⇛ Improve. Step 3 (Visual critique) has been a real problem for so long. Models will be myopic or defensive when reviewing designs - it's been hard to tell if this has been a training or a vision problem. Opus 4.5 seems to have fixed it - it's not amazing, but it finally *can* do it. Claude models have historically (once again, in my testing) lagged behind in terms of visual understanding. Gemini for the last year has been the best - but there might be a new leader.
10:06

Opus 4.5 (new model from Anthropic) can do something no model could do until now: It can close the design loop. This is (in my testing) the first model that can reliably do the visual loop of Generate Code ⇛ Render ⇛ Look at it ⇛ Improve. Step 3 (Visual critique) has been a real problem for so long. Models will be myopic or defensive when reviewing designs - it's been hard to tell if this has been a training or a vision problem. Opus 4.5 seems to have fixed it - it's not amazing, but it finally *can* do it. Claude models have historically (once again, in my testing) lagged behind in terms of visual understanding. Gemini for the last year has been the best - but there might be a new leader.

Hrishi

58,331 просмотров • 11 месяцев назад

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):
1:12

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 просмотров • 9 месяцев назад

WAIT I TAKE IT ALL BACK. MOST CONSISTENT VTUBER MODEL DESIGNS OF ALL TIME. 😌
0:33

WAIT I TAKE IT ALL BACK. MOST CONSISTENT VTUBER MODEL DESIGNS OF ALL TIME. 😌

Nythaedra VT

14,975 просмотров • 5 месяцев назад

introducing Visual Copilot - a new AI model to convert designs to high quality, responsive code in record time full announcement:
11:21

introducing Visual Copilot - a new AI model to convert designs to high quality, responsive code in record time full announcement:

Steve (Builder.io)

69,913 просмотров • 3 лет назад

We're excited to launch OpenAI's 4o image model in Playground today so you can make powerful edits to designs. We have a different spin on it: today we're launching 4 new tools for customers to change styles, colors, and put designs in mockups. In the coming weeks, we'll be releasing more tools to go beyond the prompt box. Go playground․com to try it out!
0:24

We're excited to launch OpenAI's 4o image model in Playground today so you can make powerful edits to designs. We have a different spin on it: today we're launching 4 new tools for customers to change styles, colors, and put designs in mockups. In the coming weeks, we'll be releasing more tools to go beyond the prompt box. Go playground․com to try it out!

Suhail

174,228 просмотров • 1 год назад

If you're a frontend dev let me make your life easier: 1. Pay for mobbin. 2. Setup mobbin MCP 3. Model will be able to pull all designs off the screens 4. Basically tons of free Figma designs
0:35

If you're a frontend dev let me make your life easier: 1. Pay for mobbin. 2. Setup mobbin MCP 3. Model will be able to pull all designs off the screens 4. Basically tons of free Figma designs

0xSero

74,682 просмотров • 5 месяцев назад

If you still think AI sucks at design check this out. You need a really detailed design system but amazing on brand designs are possible in Claude. Very proud of this. I’ll send my design system if people want to see it to model theirs.
0:35

If you still think AI sucks at design check this out. You need a really detailed design system but amazing on brand designs are possible in Claude. Very proud of this. I’ll send my design system if people want to see it to model theirs.

Cody Plofker

61,102 просмотров • 6 месяцев назад

Ant Group InclusionAI just released a new image model 🔥 Ming Image-0.1 Design - 6B + MIT licensed - Focused on text rich design - Native RGBA / transparent backgrounds - #1 open model on AA’s UI/UX leaderboard
0:43

Ant Group InclusionAI just released a new image model 🔥 Ming Image-0.1 Design - 6B + MIT licensed - Focused on text rich design - Native RGBA / transparent backgrounds - #1 open model on AA’s UI/UX leaderboard

Adina Yakup

16,176 просмотров • 1 месяц назад

New: You can now make transparent image layers to level up and control your designs. Playground will automatically make it in the style of your design.
0:22

New: You can now make transparent image layers to level up and control your designs. Playground will automatically make it in the style of your design.

Playground

12,364 просмотров • 1 год назад

Exciting milestones in our generative AI research: Emu Video, which lets you create high quality videos from a text prompt, and Emu Edit, which enables detailed image editing based on your instructions. These new models are built on Emu, our foundation model for image generation and technology from them will underpin new creative features across our apps next year. Try it out: Emu Video: Emu Edit:
0:37

Exciting milestones in our generative AI research: Emu Video, which lets you create high quality videos from a text prompt, and Emu Edit, which enables detailed image editing based on your instructions. These new models are built on Emu, our foundation model for image generation and technology from them will underpin new creative features across our apps next year. Try it out: Emu Video: Emu Edit:

Boz

110,741 просмотров • 3 лет назад

Flux.2 Max is out NOW 💥 UNLIMITED for 1 month for Premium+ and Pro users The highest-quality and most consistent FLUX.2 model Built for maximum prompt adherence, multi-reference consistency, and production-ready editing at blazing speed Available for all users
0:25

Flux.2 Max is out NOW 💥 UNLIMITED for 1 month for Premium+ and Pro users The highest-quality and most consistent FLUX.2 model Built for maximum prompt adherence, multi-reference consistency, and production-ready editing at blazing speed Available for all users

Magnific

24,333 просмотров • 10 месяцев назад

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.
0:36

TokenFlow: Consistent Diffusion Features for Consistent Video Editing paper page: The generative AI revolution has recently expanded to videos. Nevertheless, current state-of-the-art video models are still lagging behind image models in terms of visual quality and user control over the generated content. In this work, we present a framework that harnesses the power of a text-to-image diffusion model for the task of text-driven video editing. Specifically, given a source video and a target text-prompt, our method generates a high-quality video that adheres to the target text, while preserving the spatial layout and motion of the input video. Our method is based on a key observation that consistency in the edited video can be obtained by enforcing consistency in the diffusion feature space. We achieve this by explicitly propagating diffusion features based on inter-frame correspondences, readily available in the model. Thus, our framework does not require any training or fine-tuning, and can work in conjunction with any off-the-shelf text-to-image editing method. We demonstrate state-of-the-art editing results on a variety of real-world videos.

AK

143,557 просмотров • 3 лет назад