Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Object Cutter Create high-quality HD background removal for ANY object in your image with a text prompt or bounding boxes!

Gradio's profile picture

Gradio

57,025 subscribers

136,042 Aufrufe • vor 2 Jahren •via X (Twitter)

Wissenschaft & TechnologieBildungKunst
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Gradio
Gradiovor 2 Jahren

Object Cutter Powered By Refiners Gradio App:

Profilbild von Gradio
Gradiovor 2 Jahren

Object Cutter is built by @finegrain_ai 💪This Space uses two custom components📷: > by @evilpingwin > by Edgar Gracia Larrosa (for Bounding Boxes) 🔓Finegrain-Box-Segmenter model is open sourced on @huggingface Hub and is MIT licensed🥳:

Profilbild von AI Furry Art (SFW-ish)
AI Furry Art (SFW-ish)vor 2 Jahren

All these background removal tools have the same issue for me, they cut out character's heads and treat their bodies and clothes as background.

Profilbild von NeuralNinja AI
NeuralNinja AIvor 2 Jahren

I'm excited to try Object Cutter, it looks like a powerful tool!

Profilbild von INDEX 3D
INDEX 3Dvor 2 Jahren

@kash_cg_art

Profilbild von llmstock.com mc
llmstock.com mcvor 2 Jahren

nice app

Profilbild von Gradio
Gradiovor 2 Jahren

💯

Profilbild von ___raf stahelin___
___raf stahelin___vor 2 Jahren

How about text remover

Profilbild von Critiqs AI
Critiqs AIvor 2 Jahren

Looks great

Profilbild von Sudeep Shouche
Sudeep Shouchevor 2 Jahren

This works very well, tried with a few images of scattered tiny puzzle pieces and happy with the results👍🏼

Profilbild von Gradio
Gradiovor 2 Jahren

That's great thanks for sharing!

Ähnliche Videos

Google announces InseRF Text-Driven Generative Object Insertion in Neural 3D Scenes paper page: InseRF generates an object in a 3D scene via a text prompt and one 2D bounding box
1:35

Google announces InseRF Text-Driven Generative Object Insertion in Neural 3D Scenes paper page: InseRF generates an object in a 3D scene via a text prompt and one 2D bounding box

AK

205,987 Aufrufe • vor 2 Jahren

Grok Imagine Image Quality is here sharper details at 2k. real text. edit any image with a prompt
0:30

Grok Imagine Image Quality is here sharper details at 2k. real text. edit any image with a prompt

Replicate

10,976 Aufrufe • vor 4 Monaten

Higgsfield Mod for Minecraft is live. > prompt any building or city, even the Statue of Liberty > create paintings with text-to-image > snap a view and restyle it with image-to-image > make videos from a prompt with text-to-video. > animate in-game photos with image-to-video
0:34

Higgsfield Mod for Minecraft is live. > prompt any building or city, even the Statue of Liberty > create paintings with text-to-image > snap a view and restyle it with image-to-image > make videos from a prompt with text-to-video. > animate in-game photos with image-to-video

Higgsfield AI 🧩

462,693 Aufrufe • vor 3 Monaten

⚡️ New on Lovart: Move Object → Select any object with rectangular or lasso tool → Move it wherever you want → Prompt optional modifications → One clean, consistent image No masks. No layers. No re-roll.
0:39

⚡️ New on Lovart: Move Object → Select any object with rectangular or lasso tool → Move it wherever you want → Prompt optional modifications → One clean, consistent image No masks. No layers. No re-roll.

LovartAI

515,519 Aufrufe • vor 5 Monaten

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 🧩

292,412 Aufrufe • vor 1 Monat

🔥 DreamEngine revolutionizes image generation with its text-guided object fusion capabilities! The demo and code for Text Guided Object Fustion are released! Let's unlock the Imaginations! Run it locally now in: Paper:
0:27

🔥 DreamEngine revolutionizes image generation with its text-guided object fusion capabilities! The demo and code for Text Guided Object Fustion are released! Let's unlock the Imaginations! Run it locally now in: Paper:

Liang Chen

11,376 Aufrufe • vor 1 Jahr

Introducing Agentic Object Detection! Given a text prompt like “unripe strawberries” or “Kellogg’s branded cereal” and an image, we use an agentic workflow to reason at length and detect the specified objects. No need to label any training data. Watch the video for details.
2:09

Introducing Agentic Object Detection! Given a text prompt like “unripe strawberries” or “Kellogg’s branded cereal” and an image, we use an agentic workflow to reason at length and detect the specified objects. No need to label any training data. Watch the video for details.

Andrew Ng

398,060 Aufrufe • vor 1 Jahr

Three new open-source models just landed in ComfyUI natively: → Gemma 4 (Google DeepMind) - multimodal LLM handling text, image, audio, and video input with built-in step-by-step reasoning mode → VOID (Netflix) - video object removal that also erases shadows, reflections, and physical interactions caused by the removed subject → BiRefNet - high-res background & object segmentation, one of the most-used segmentation models in the ecosystem Workflows and blog linked below 👇
0:20

Three new open-source models just landed in ComfyUI natively: → Gemma 4 (Google DeepMind) - multimodal LLM handling text, image, audio, and video input with built-in step-by-step reasoning mode → VOID (Netflix) - video object removal that also erases shadows, reflections, and physical interactions caused by the removed subject → BiRefNet - high-res background & object segmentation, one of the most-used segmentation models in the ecosystem Workflows and blog linked below 👇

ComfyUI

218,749 Aufrufe • vor 3 Monaten

This is amazing! You can now create high-quality 3D Scenes from a single image using Multi-Instance Diffusion Models (MIDI) 🔥
0:43

This is amazing! You can now create high-quality 3D Scenes from a single image using Multi-Instance Diffusion Models (MIDI) 🔥

Gradio

41,940 Aufrufe • vor 1 Jahr

ElevenLabs Music is here. Generate studio-quality tracks instantly in any genre, style, vocals or instrumental, all with a simple text prompt.
0:30

ElevenLabs Music is here. Generate studio-quality tracks instantly in any genre, style, vocals or instrumental, all with a simple text prompt.

Replicate

27,753 Aufrufe • vor 10 Monaten

With Replit ⠕ Design, you can create high-quality scroll animations for your landing pages in under five minutes— all from a single prompt.
0:22

With Replit ⠕ Design, you can create high-quality scroll animations for your landing pages in under five minutes— all from a single prompt.

Vaibhav Kumar

180,359 Aufrufe • vor 8 Monaten

Copy + paste! Create 3D models of real world items, like magic, by just circling an object or an image with your finger. Resize and place it in your space with "Ctrl+C" by Tejas Shroff.
0:25

Copy + paste! Create 3D models of real world items, like magic, by just circling an object or an image with your finger. Resize and place it in your space with "Ctrl+C" by Tejas Shroff.

Spectacles

17,341 Aufrufe • vor 8 Monaten

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.
2:16

How can we learn 3D visual grounding with natural supervision—only looking at QA pairs, without ground truth bounding boxes or object classification labels? We inject explicit language priors, e.g., the symmetric property that A near B ⇒ B near A, in structured vision models.

Joy Hsu

14,843 Aufrufe • vor 2 Jahren

Code released: "GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting"
1:10

Code released: "GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting"

MrNeRF

22,279 Aufrufe • vor 2 Jahren

Do more with Glass → Add it to any object, shape, or text → Round individual corners → Adjust the spread of light refraction with Splay → Apply variables from your design system
0:29

Do more with Glass → Add it to any object, shape, or text → Round individual corners → Adjust the spread of light refraction with Splay → Apply variables from your design system

Figma

1,138,003 Aufrufe • vor 7 Monaten

Today we're releasing WildDet3D—an open model for monocular 3D object detection in the wild. It works with text, clicks, or 2D boxes, and on zero-shot evals it nearly doubles the best prior scores. 🧵
0:57

Today we're releasing WildDet3D—an open model for monocular 3D object detection in the wild. It works with text, clicks, or 2D boxes, and on zero-shot evals it nearly doubles the best prior scores. 🧵

Ai2

87,433 Aufrufe • vor 5 Monaten