Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Introducing Underdog Images: on-device Image Gen Generate any image, or drop in a photo and say what to change. It all runs on your device. Your photos never leave your computer Made with Qwen-Image Flash from NVIDIA AI and Qwen-Image-2.1-Turbo from Qwen

Underdog AI

7,334 subscribers

33,098 Aufrufe • vor 3 Tagen •via X (Twitter)

Kunst Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

34 Kommentare

Profilbild von Underdog AI

Underdog AIvor 3 Tagen

Try generating images for free at

Profilbild von Sigil Wen

Sigil Wenvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen this is so cute

Profilbild von Underdog AI

Underdog AIvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen 🐶thank u human

Profilbild von ada cyborg (🤖, 🔮)

ada cyborg (🤖, 🔮)vor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Wowww i want the dog hosts 😍

Profilbild von Underdog AI

Underdog AIvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Coming 🔜

Profilbild von ILLIAN BOLIVAR

ILLIAN BOLIVARvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen 🤯🤔🤯🤔

Profilbild von Dr. Parik Patel, BA, CFA, ACCA Esq.

Dr. Parik Patel, BA, CFA, ACCA Esq.vor 3 Tagen

@0xSigil @NVIDIAAI @Alibaba_Qwen Cool!

Profilbild von Ben

Benvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Bro this is insane @0xSigil

Profilbild von Matt Van Horn

Matt Van Hornvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen whoa.

Profilbild von Ivan Fioravanti

Ivan Fioravantivor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Local AI to the max! Well done!

Profilbild von Amelia | AI & Tech

Amelia | AI & Techvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Finally image generation that actually respects privacy

Profilbild von Adi

Adivor 2 Tagen

@NVIDIAAI @Alibaba_Qwen that's really cool!

Profilbild von ZenithAi

ZenithAivor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Private on-device creativity makes image generation far more appealing

Profilbild von Captain

Captainvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Just brilliant, all local on laptop!

Profilbild von jacky

jackyvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen What's the minimum VRAM for the Qwen-Image-2.1-Turbo path? That decides whether on-device means a normal laptop or a gaming rig.

Profilbild von Mvhmd

Mvhmdvor 3 Tagen

@0xSigil @NVIDIAAI @Alibaba_Qwen Need invite asap

Profilbild von YoYix.BNB

YoYix.BNBvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen local model goes hard

Profilbild von BitAres

BitAresvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Does editing save a new copy, so the original photo stays untouched?

Profilbild von Lee Boway Nitrograph 🌶️

Lee Boway Nitrograph 🌶️vor 3 Tagen

@NVIDIAAI @Alibaba_Qwen I want it!

Profilbild von RAZA | AI EXPLORER

RAZA | AI EXPLORERvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen On-device image generation with privacy at its core. Love seeing powerful AI tools that keep your data local.

Profilbild von eastboy

eastboyvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen nice. good job. how to get the invite pls?

Profilbild von Yitzy Mytelka

Yitzy Mytelkavor 3 Tagen

@NVIDIAAI @Alibaba_Qwen IMO yall shouldve waited on this one. focused on the more useful things, and in a year or two, worked on an image model.

Profilbild von Underdog AI

Underdog AIvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen shipping another utility feature very soon. shipped Underdog Images because the weights were just dropped just yesterday One fun drop, one useful drop everyday :)

Profilbild von Alice The Ai Expert

Alice The Ai Expertvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Love the privacy first approach powerful on device generation without your photos ever leaving your device!

Profilbild von Oguz.ETH

Oguz.ETHvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen local gpu gonna fry

Profilbild von fiber reis

fiber reisvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Could you please send me an invite to try out the platform?

Profilbild von F A X I I I 7

F A X I I I 7vor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Hey looks like underdog needs an invite? can i have one?

Profilbild von Nova Tech

Nova Techvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen On device privacy is the future

Profilbild von Liam | AI Tools & News

Liam | AI Tools & Newsvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen My GPU just got promoted from gaming machine to personal art department.

Profilbild von AndreaPN

AndreaPNvor 3 Tagen

@0xSigil @NVIDIAAI @Alibaba_Qwen 👀

Profilbild von Veyra | AI & Tech

Veyra | AI & Techvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen On device edits keep your photos completely local

Profilbild von Elise Tech Ai

Elise Tech Aivor 3 Tagen

@NVIDIAAI @Alibaba_Qwen Underdog Images running fully on-device is awesome, privacy first image gen

Profilbild von Antho G

Antho Gvor 2 Tagen

@NVIDIAAI @Alibaba_Qwen Can't be used for commercial then?

Profilbild von EDDY VU

EDDY VUvor 3 Tagen

@NVIDIAAI @Alibaba_Qwen What are the minimum VRAM specs to get solid generation speeds running this locally?

Ähnliche Videos

Qwen-Image-2.1-viggle-turbo v0.2 is out on Hugging Face Text-to-image and image editing in 6 steps about 5× faster than the 40-step Qwen-Image-2.1 model:

Qwen-Image-2.1-viggle-turbo v0.2 is out on Hugging Face Text-to-image and image editing in 6 steps about 5× faster than the 40-step Qwen-Image-2.1 model:

AK

46,185 Aufrufe • vor 19 Tagen

Qwen-Image-2.1 in 4 steps is here ⚡ ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model ▶️ on Spaces

Qwen-Image-2.1 in 4 steps is here ⚡ ViggleAI distilled Qwen-Image-2.1 into a 4-step turbo model, 6× faster, and holds up side by side with the full model ▶️ on Spaces

Hugging Apps

95,752 Aufrufe • vor 21 Tagen

Qwen Image 2.1 Turbo + Pro is now on Venice. Generate native 2K images with transparent backgrounds, edit from up to 10 reference images, and render text you can actually read. Available anonymously.

Qwen Image 2.1 Turbo + Pro is now on Venice. Generate native 2K images with transparent backgrounds, edit from up to 10 reference images, and render text you can actually read. Available anonymously.

Venice

11,564 Aufrufe • vor 3 Tagen

Pruna-Qwen-Image-2.1 a set of a few-step LoRA adapters that make Qwen-Image-2.1 up to 6.3× faster for image generation and editing Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance HF workflow:

Pruna-Qwen-Image-2.1 a set of a few-step LoRA adapters that make Qwen-Image-2.1 up to 6.3× faster for image generation and editing Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance HF workflow:

AK

23,179 Aufrufe • vor 20 Tagen

Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2.1 by Qwen up to 6.3× faster for image generation and editing. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? The 8-step adapter is our recommended default. It supports text-to-image and single- or multi-image editing at 1K resolution, with up to three reference images. - 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸?The LoRA adapters load directly on top of Qwen-Image-2.1, while the pipeline remains unchanged. Each adapter uses its own optimized sigma schedule and runs without CFG. 𝘛𝘩𝘪𝘴 𝘪𝘴 𝘫𝘶𝘴𝘵 𝘰𝘶𝘳 𝘧𝘪𝘳𝘴𝘵 𝘳𝘦𝘭𝘦𝘢𝘴𝘦, 𝘸𝘪𝘵𝘩 𝘦𝘷𝘦𝘯 𝘣𝘦𝘵𝘵𝘦𝘳 𝘷𝘦𝘳𝘴𝘪𝘰𝘯𝘴 𝘰𝘯 𝘵𝘩𝘦 𝘸𝘢𝘺. 🚀 Want to try the fast open-source integration? Check it here on Diffusers: Want to try the fastest image generation and editing endpoint? Check P-Image-Ideogram and P-Image-Edit here on API:

Today, we open-source Pruna-Qwen-Image-2.1, a set of a few-step LoRA adapters that make Qwen-Image-2.1 by Qwen up to 6.3× faster for image generation and editing. - 𝗛𝗼𝘄 𝗲𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁 𝗶𝘀 𝗶𝘁? Generate or edit images in just 5 or 8 steps instead of 40. Choose 5 steps for maximum speed or 8 steps for the best balance. - 𝗛𝗼𝘄 𝗴𝗼𝗼𝗱 𝗶𝘀 𝗶𝘁? The 8-step adapter is our recommended default. It supports text-to-image and single- or multi-image editing at 1K resolution, with up to three reference images. - 𝗛𝗼𝘄 𝗱𝗼𝗲𝘀 𝗶𝘁 𝘄𝗼𝗿𝗸?The LoRA adapters load directly on top of Qwen-Image-2.1, while the pipeline remains unchanged. Each adapter uses its own optimized sigma schedule and runs without CFG. 𝘛𝘩𝘪𝘴 𝘪𝘴 𝘫𝘶𝘴𝘵 𝘰𝘶𝘳 𝘧𝘪𝘳𝘴𝘵 𝘳𝘦𝘭𝘦𝘢𝘴𝘦, 𝘸𝘪𝘵𝘩 𝘦𝘷𝘦𝘯 𝘣𝘦𝘵𝘵𝘦𝘳 𝘷𝘦𝘳𝘴𝘪𝘰𝘯𝘴 𝘰𝘯 𝘵𝘩𝘦 𝘸𝘢𝘺. 🚀 Want to try the fast open-source integration? Check it here on Diffusers: Want to try the fastest image generation and editing endpoint? Check P-Image-Ideogram and P-Image-Edit here on API:

Pruna AI

90,322 Aufrufe • vor 20 Tagen

Image analysis is now live for Pro users When you drag and drop an image into the input field Venice now auto-selects Qwen 2.5 VL 72B to analyze your image

Image analysis is now live for Pro users When you drag and drop an image into the input field Venice now auto-selects Qwen 2.5 VL 72B to analyze your image

Venice

53,786 Aufrufe • vor 1 Jahr

We have updated image generation models with Nano Banana, Qwen-image, and Seedream 4.0, now enabling direct image-to-video creation. Up to 4k images generation. Stremline your workflow! -> Retweet to get 300 credits in DMs (72H ONLY)

We have updated image generation models with Nano Banana, Qwen-image, and Seedream 4.0, now enabling direct image-to-video creation. Up to 4k images generation. Stremline your workflow! -> Retweet to get 300 credits in DMs (72H ONLY)

PixVerse

76,804 Aufrufe • vor 11 Monaten

Qwen Image 2.1 is here! 🖼️ A 7B params native image generation and editing model, with up to 10 image references The model comes with it's own prompt enhancement LLMs, integrated with diffusers 🧨 and ComfyUI ▶️ on Spaces

Qwen Image 2.1 is here! 🖼️ A 7B params native image generation and editing model, with up to 10 image references The model comes with it's own prompt enhancement LLMs, integrated with diffusers 🧨 and ComfyUI ▶️ on Spaces

Hugging Apps

91,083 Aufrufe • vor 24 Tagen

A full coffee brand built from scratch: story, voice, mascot, landing page, and a launch thread. Created using Qwen 3.7 and Qwen Image Edit 2, all with anonymized conversations through Venice, shielding your identity from the model providers.

Venice

19,008 Aufrufe • vor 3 Monaten

Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included

Qwen-Image-2.1 is now supported in ComfyUI! Open weights. One 7B checkpoint that generates and edits. → Image generation at native 2K → Instruction editing from up to 10 reference images in a single pass → RGBA output, alpha included

ComfyUI

194,270 Aufrufe • vor 24 Tagen

one PNG in, every angle out 🔄 a viewpoint-orbit LoRA for Qwen-Image-2.1: upload one transparent image and it walks the camera around the object, back view included, transparency kept ▶️ on Spaces

one PNG in, every angle out 🔄 a viewpoint-orbit LoRA for Qwen-Image-2.1: upload one transparent image and it walks the camera around the object, back view included, transparency kept ▶️ on Spaces

Hugging Apps

15,835 Aufrufe • vor 17 Tagen

Qwen‑Image‑3.0 is built for complex content creation, from detailed knowledge diagrams to UI interfaces, all in one step. With ultra‑long inputs of up to 4.5K tokens and native rendering in 12 languages, Qwen‑Image‑3.0 unlocks new possibilities for creators and developers alike. 🎨Discover what you can build next!

Qwen‑Image‑3.0 is built for complex content creation, from detailed knowledge diagrams to UI interfaces, all in one step. With ultra‑long inputs of up to 4.5K tokens and native rendering in 12 languages, Qwen‑Image‑3.0 unlocks new possibilities for creators and developers alike. 🎨Discover what you can build next!

Alibaba Group

3,134,106 Aufrufe • vor 2 Monaten

Qwen‑Image‑2.0 continues to push what’s possible in next‑gen image generation. From pro typography rendering and stronger semantic adherence to improved text rendering and a lighter model, it keeps delivering creative power with ease. Check out the demos to discover more!

Qwen‑Image‑2.0 continues to push what’s possible in next‑gen image generation. From pro typography rendering and stronger semantic adherence to improved text rendering and a lighter model, it keeps delivering creative power with ease. Check out the demos to discover more!

Alibaba Cloud

928,486 Aufrufe • vor 6 Monaten

Introducing Hano — 3D device mockups that run in your browser. No install. Drop in a screenshot, pick a device, export a 4K image or animated video in minutes. and this video? Made with Hano. Try for free.

Introducing Hano — 3D device mockups that run in your browser. No install. Drop in a screenshot, pick a device, export a 4K image or animated video in minutes. and this video? Made with Hano. Try for free.

Shaig

26,215 Aufrufe • vor 3 Monaten

Introducing Manus image generation. Manus doesn’t just generate images. It understands your intent, plans a solution, and knows how to effectively use image generation along with other tools to accomplish your task.

Introducing Manus image generation. Manus doesn’t just generate images. It understands your intent, plans a solution, and knows how to effectively use image generation along with other tools to accomplish your task.

Manus

178,317 Aufrufe • vor 1 Jahr

Private AI browser with the OpenClaw agent on free local models Run your agent on Qwen, Gemma, or Nemotron directly in the browser Open source. Private. Runs on your local device

Private AI browser with the OpenClaw agent on free local models Run your agent on Qwen, Gemma, or Nemotron directly in the browser Open source. Private. Runs on your local device

Sigma Browser

115,918 Aufrufe • vor 5 Monaten

There’s a new way to bring your still images to life on The Render Network You can now upload your own images – from renders and art to selfies, pets, or product shots & more using Image-to-Image or Image-to-Video Models on Render. Check it out at and start creating today!

There’s a new way to bring your still images to life on The Render Network You can now upload your own images – from renders and art to selfies, pets, or product shots & more using Image-to-Image or Image-to-Video Models on Render. Check it out at and start creating today!

The Render Network

38,029 Aufrufe • vor 1 Jahr