Loading video...

Video Failed to Load

Go Home

Zero-shot Image Editing with Reference Imitation Image editing serves as a practical yet challenging task considering the diverse demands from users, where one of the hardest parts is to precisely describe how the edited image should look like. In this work, we

_akhaliq's profile picture

AK

508,449 subscribers

43,538 views • 2 years ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

How to use Grok's Image Editing Feature? Click "Edit Image," upload your image, and describe the changes you want to make.
0:22

How to use Grok's Image Editing Feature? Click "Edit Image," upload your image, and describe the changes you want to make.

DogeDesigner

99,687 views • 1 year ago

1. Precise Edits Made Easy Image editing has never been simpler. No need to type out prompts, just talk to the AI and describe exactly how you want the image edited.
0:21

1. Precise Edits Made Easy Image editing has never been simpler. No need to type out prompts, just talk to the AI and describe exactly how you want the image edited.

el.cine

98,422 views • 1 year ago

Reve just launched and the early results are 🤯 🎨 Spatially intelligent generation, create multi-image layouts in one shot 🖌️ Reference images to craft the perfect scene 🎭️ State of the art image editing capabilities
0:47

Reve just launched and the early results are 🤯 🎨 Spatially intelligent generation, create multi-image layouts in one shot 🖌️ Reference images to craft the perfect scene 🎭️ State of the art image editing capabilities

fal

31,292 views • 8 months ago

Here’s what we are working on at Adobe Layered image editing 🤯 the future of AI image editing
0:25

Here’s what we are working on at Adobe Layered image editing 🤯 the future of AI image editing

Kris Kashtanova

59,825 views • 8 months ago

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.
0:22

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 views • 1 year ago

Excited to share a Google DeepMind Gemini 2.0 Flash Image Generation and Editing Quickstart. We build a Next.js reference app on how to use the new image editing feature of Gemini 2.0 Flash. Demo to test ⬇️ > Generate images from text prompts using Gemini 2.0 Flash > Or upload an image and edit it using prompts
0:48

Excited to share a Google DeepMind Gemini 2.0 Flash Image Generation and Editing Quickstart. We build a Next.js reference app on how to use the new image editing feature of Gemini 2.0 Flash. Demo to test ⬇️ > Generate images from text prompts using Gemini 2.0 Flash > Or upload an image and edit it using prompts

Philipp Schmid

52,406 views • 1 year ago

Step into the future of AI image generation with Qwen-Image! From superior text rendering to consistent image editing across multiple languages, it sets a new benchmark! 💡What will you create with Qwen-Image?
0:28

Step into the future of AI image generation with Qwen-Image! From superior text rendering to consistent image editing across multiple languages, it sets a new benchmark! 💡What will you create with Qwen-Image?

Alibaba Group

203,475 views • 10 months ago

🚀 Q2 Image Model is Live! ✨Text to image, Reference to image, and Image editing supported ✨Ultra-fast generation (as fast as 5s), 4K quality, super consistency ✨One-stop workflow: turn reference images into subjects and reuse them for video creation ✨Unlimited image generation for members until Dec 31 New users: use code VIDUQ2RTI for bonus credits 🎁 #ViduQ2RTI #ViduQ2 #Viduai #vidu
0:57

🚀 Q2 Image Model is Live! ✨Text to image, Reference to image, and Image editing supported ✨Ultra-fast generation (as fast as 5s), 4K quality, super consistency ✨One-stop workflow: turn reference images into subjects and reuse them for video creation ✨Unlimited image generation for members until Dec 31 New users: use code VIDUQ2RTI for bonus credits 🎁 #ViduQ2RTI #ViduQ2 #Viduai #vidu

Vidu AI

24,747 views • 7 months ago

Complete story entirely created with Grok Imagine 4.20: -Image, image editing, image reference -video, Images for video reference, video extension I did in a few hours what used to take me weeks and of much better quality!
2:32

Complete story entirely created with Grok Imagine 4.20: -Image, image editing, image reference -video, Images for video reference, video extension I did in a few hours what used to take me weeks and of much better quality!

Déborah

57,945 views • 3 months ago

MagicQuill MagicQuill is a dead simple image editing app powered by AI, running on Gradio. What sets this apart is, there is ZERO learning curve. Just start with an image and ask the AI to change it. This launcher was created by Morpheus (most pinokio users should know him!)
1:45

MagicQuill MagicQuill is a dead simple image editing app powered by AI, running on Gradio. What sets this apart is, there is ZERO learning curve. Just start with an image and ask the AI to change it. This launcher was created by Morpheus (most pinokio users should know him!)

cocktail peanut

29,751 views • 1 year ago

📸 Introducing Replicate Image Editing Arena. We heard you needed an easy way to compare all of the latest image editing models. Evaluate models like FLUX.2, Nano Banana, Seedream, Qwen Edit, and Reve for speed, cost, and performance...all in one interface.
0:22

📸 Introducing Replicate Image Editing Arena. We heard you needed an easy way to compare all of the latest image editing models. Evaluate models like FLUX.2, Nano Banana, Seedream, Qwen Edit, and Reve for speed, cost, and performance...all in one interface.

Replicate

45,689 views • 7 months ago

InstantDrag Improving Interactivity in Drag-based Image Editing discuss: Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.
0:46

InstantDrag Improving Interactivity in Drag-based Image Editing discuss: Drag-based image editing has recently gained popularity for its interactivity and precision. However, despite the ability of text-to-image models to generate samples within a second, drag editing still lags behind due to the challenge of accurately reflecting user interaction while maintaining image content. Some existing approaches rely on computationally intensive per-image optimization or intricate guidance-based methods, requiring additional inputs such as masks for movable regions and text prompts, thereby compromising the interactivity of the editing process. We introduce InstantDrag, an optimization-free pipeline that enhances interactivity and speed, requiring only an image and a drag instruction as input. InstantDrag consists of two carefully designed networks: a drag-conditioned optical flow generator (FlowGen) and an optical flow-conditioned diffusion model (FlowDiffusion). InstantDrag learns motion dynamics for drag-based image editing in real-world video datasets by decomposing the task into motion generation and motion-conditioned image generation. We demonstrate InstantDrag's capability to perform fast, photo-realistic edits without masks or text prompts through experiments on facial video datasets and general scenes. These results highlight the efficiency of our approach in handling drag-based image editing, making it a promising solution for interactive, real-time applications.

AK

71,228 views • 1 year ago

Fable 5 made monica apartment in one shot without any image reference 😱 you can see how opus 4.5 performed with image reference and guidance
0:33

Fable 5 made monica apartment in one shot without any image reference 😱 you can see how opus 4.5 performed with image reference and guidance

Chetaslua

22,688 views • 20 days ago

Image editing in the Google Gemini just got a major upgrade.
0:45

Image editing in the Google Gemini just got a major upgrade.

Google

151,271 views • 10 months ago

gpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering.
0:56

gpt-image-2 is here, available today in the API and Codex. The most capable image generation model yet, built for production-grade workflows with stronger text rendering, layout, editing, resolution, and multilingual rendering.

OpenAI Developers

181,538 views • 2 months ago

Introducing Higgsfield Canvas: a state-of-the-art image editing model. Paint products directly onto your image with pixel-perfect control. Say hi to your new go-to for product placement, editing, and layout! 👋🏻 Comment Canvas to get the full guide in the DM.
0:26

Introducing Higgsfield Canvas: a state-of-the-art image editing model. Paint products directly onto your image with pixel-perfect control. Say hi to your new go-to for product placement, editing, and layout! 👋🏻 Comment Canvas to get the full guide in the DM.

Higgsfield AI 🧩

2,627,211 views • 1 year ago

GoogleAI just released "Muse", a text-to-image generation/editing model via Masked Generative Transformers: - Achieves new SOTA - Zero-shot, Mask-free editing - Zero-shot Inpainting/Outpainting - 900M params 📄 Paper: ⚙️ Project:
0:27

GoogleAI just released "Muse", a text-to-image generation/editing model via Masked Generative Transformers: - Achieves new SOTA - Zero-shot, Mask-free editing - Zero-shot Inpainting/Outpainting - 900M params 📄 Paper: ⚙️ Project:

Lior Alexander

630,453 views • 3 years ago

New art project: the concept is to carve an image into wood in a semi-abstract form that allows the viewer to both recognize and personalize the image. The image is carved as an array of precisely cut dimples in a piece of pale wood pre-coated with black paint. 1/7
0:44

New art project: the concept is to carve an image into wood in a semi-abstract form that allows the viewer to both recognize and personalize the image. The image is carved as an array of precisely cut dimples in a piece of pale wood pre-coated with black paint. 1/7

David R. Liu

85,057 views • 2 years ago

Qwen-Image-Edit is out in anycoder for image editing in your vibe coded apps Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing.
1:25

Qwen-Image-Edit is out in anycoder for image editing in your vibe coded apps Built on 20B Qwen-Image, it brings precise bilingual text editing (Chinese & English) while preserving style, and supports both semantic and appearance-level editing.

AK

119,012 views • 10 months ago

🕹️We are excited to introduce "ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation" ChronoEdit reframes image editing as a video generation task to encourage temporal consistency. It leverages a temporal reasoning stage that denoises with “video reasoning tokens” to "reason" on physically plausible edits. See the attached video for results. Project Page: Arxiv: Code and model are coming.
1:38

🕹️We are excited to introduce "ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation" ChronoEdit reframes image editing as a video generation task to encourage temporal consistency. It leverages a temporal reasoning stage that denoises with “video reasoning tokens” to "reason" on physically plausible edits. See the attached video for results. Project Page: Arxiv: Code and model are coming.

Huan Ling

36,869 views • 8 months ago