Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Found a hardcore LoRA workflow! Generate a PLY point cloud --> Adjust angle in editor -->Refine with Qwen-Image-Edit-2511 Gaussian Splash LoRA. It accurately restores complex perspective shifts. As shown in the demo, it handles 3D rotation and can even restore high-def details from blurry close-ups. Within a 45° range,...

Ali_TongyiLab's profile picture

Tongyi Lab

24,878 subscribers

1,493,347 görüntüleme • 5 ay önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

This is huge!! Spline now supports Gaussian splats 👀 You can now capture anything in 3D from your phone with Luma, export the .ply file, import it into spline, crop, adjust, and embed on your site. Luma + Spline + Webflow is an insane 3D workflow 🔥
0:37

This is huge!! Spline now supports Gaussian splats 👀 You can now capture anything in 3D from your phone with Luma, export the .ply file, import it into spline, crop, adjust, and embed on your site. Luma + Spline + Webflow is an insane 3D workflow 🔥

Nick St. Pierre

1,139,640 görüntüleme • 2 yıl önce

SDR to HDR from ComfyUI, I've trained a LoRA over Qwen Edit 2011 based on the principle used in A research I've had the previlige to work on with Naomi Ken Korem for video HDR on LTX. Links for the LoRA and workflow (+ my fun grading node) below.
1:09

SDR to HDR from ComfyUI, I've trained a LoRA over Qwen Edit 2011 based on the principle used in A research I've had the previlige to work on with Naomi Ken Korem for video HDR on LTX. Links for the LoRA and workflow (+ my fun grading node) below.

Mohamed Oumoumad

58,664 görüntüleme • 2 ay önce

LoRA training is the standout feature. You can fine tune Qwen Image directly online, export the trained LoRA, and plug it straight into ComfyUI workflows like any custom model. This replaces a lot of paid LoRA setups.
0:40

LoRA training is the standout feature. You can fine tune Qwen Image directly online, export the trained LoRA, and plug it straight into ComfyUI workflows like any custom model. This replaces a lot of paid LoRA setups.

SANI BULA

15,462 görüntüleme • 4 ay önce

This is a Lora application for generating multiple characters. It can generate characters suitable for any scene from almost any angle, and it can generate multiple characters. Tongyi Lab This is what my colleague trained.
1:47

This is a Lora application for generating multiple characters. It can generate characters suitable for any scene from almost any angle, and it can generate multiple characters. Tongyi Lab This is what my colleague trained.

大雄

36,366 görüntüleme • 7 ay önce

fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA 角度変更、めちゃくちゃ精度高くてすごい Qwen Image Multiple Angles 3D Camera - a Hugging Face Space by multimodalart
0:38

fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA 角度変更、めちゃくちゃ精度高くてすごい Qwen Image Multiple Angles 3D Camera - a Hugging Face Space by multimodalart

とよふく🎍Toyofuku

727,952 görüntüleme • 5 ay önce

Qwen-Edit-2511 Upscale2K LoRA has been updated. Impressive results. Sometimes there are unexpected changes, but it’s still useful for general image improvements.
0:42

Qwen-Edit-2511 Upscale2K LoRA has been updated. Impressive results. Sometimes there are unexpected changes, but it’s still useful for general image improvements.

Wildminder

51,501 görüntüleme • 5 ay önce

Open-source might have just caught up to NanoBanana dx8152 trained a Qwen Edit LoRA that nails multi-angle shots. Here’s a product video I made using it with Kling Start/End frames. Link to LoRA below 👇
0:20

Open-source might have just caught up to NanoBanana dx8152 trained a Qwen Edit LoRA that nails multi-angle shots. Here’s a product video I made using it with Kling Start/End frames. Link to LoRA below 👇

Miguel | AP

61,137 görüntüleme • 7 ay önce

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian
0:58

More and more users are turning their 360 footage into fully explorable 3D Gaussian Splats with View it here: This reconstruction started from a simple capture and is now a fully explorable 3D Gaussian Splat rendered in the FreeGaussian viewer, complete with point cloud reconstruction and high-fidelity spatial detail. More and more creators are discovering that their existing footage can become immersive 3D scenes. And they’re doing it for free with FreeGaussian

Over the Reality 🌐

14,662 görüntüleme • 1 ay önce

🥳 Qwen-Image-Edit-2511 on 🍞 TostUI 🧪 (tested on RTX 3090/4090/5090, Windows & Linux, 8bit) Thanks to Qwen Team ❤ 🐋 docker run --gpus all -p 3000:3000 --name tostui-qwen-image-edit-2511 camenduru/tostui-qwen-image-edit-2511 🍞
0:57

🥳 Qwen-Image-Edit-2511 on 🍞 TostUI 🧪 (tested on RTX 3090/4090/5090, Windows & Linux, 8bit) Thanks to Qwen Team ❤ 🐋 docker run --gpus all -p 3000:3000 --name tostui-qwen-image-edit-2511 camenduru/tostui-qwen-image-edit-2511 🍞

camenduru

41,027 görüntüleme • 6 ay önce

Here's the demo "Enhance This"! It's a surreal image magnifier that creates a high-res version by imagining new details, using the SDXL base model. Thanks to Ruoyi Du's DemoFusion research. It takes a ~minute to generate a 2024x2024 image.
0:35

Here's the demo "Enhance This"! It's a surreal image magnifier that creates a high-res version by imagining new details, using the SDXL base model. Thanks to Ruoyi Du's DemoFusion research. It takes a ~minute to generate a 2024x2024 image.

Radamés Ajna

227,953 görüntüleme • 2 yıl önce

still experimenting with LoRA based on the Thinking Machines configuration and just implemented it in colab. In this notebook I set up a fine tune of Qwen/Qwen3-0.6B on the OpenR1-Math dataset with lora rank of 1. with this setup you can get the same reward accuracy as full fine-tuning, at a fraction of vram usage.
0:45

still experimenting with LoRA based on the Thinking Machines configuration and just implemented it in colab. In this notebook I set up a fine tune of Qwen/Qwen3-0.6B on the OpenR1-Math dataset with lora rank of 1. with this setup you can get the same reward accuracy as full fine-tuning, at a fraction of vram usage.

Ben Burtenshaw

25,624 görüntüleme • 8 ay önce

ml-sharp 🤝 FLUX.2 klein Inspired by 大雄, I’ve trained a LoRA for klein 9b that can repair 3D views from ml-sharp, fixing geometry issues and restoring original details. Weights: I will share the demo + inference code soon!
1:03

ml-sharp 🤝 FLUX.2 klein Inspired by 大雄, I’ve trained a LoRA for klein 9b that can repair 3D views from ml-sharp, fixing geometry issues and restoring original details. Weights: I will share the demo + inference code soon!

Cyril Diagne

31,632 görüntüleme • 5 ay önce

We're releasing ✨Qwen Image Edit Relight✨ a dedicated Qwen Image Edit app for image relighting fast, precise and optimized for relighting no more need for a complex workflows when you can get sota outputs with as little as 8 steps
0:34

We're releasing ✨Qwen Image Edit Relight✨ a dedicated Qwen Image Edit app for image relighting fast, precise and optimized for relighting no more need for a complex workflows when you can get sota outputs with as little as 8 steps

Linoy Tsaban🎗️

19,608 görüntüleme • 10 ay önce

📢ProcGen3D: Learning Neural Procedural Graphs for Image-to-3D Reconstruction Xinyi Zhang learns neural procedural graphs to generate high-fidelity 3D - MCTS-guided sampling maintains consistency with the input image, even from real images! Check it out:
0:38

📢ProcGen3D: Learning Neural Procedural Graphs for Image-to-3D Reconstruction Xinyi Zhang learns neural procedural graphs to generate high-fidelity 3D - MCTS-guided sampling maintains consistency with the input image, even from real images! Check it out:

Angela Dai

14,590 görüntüleme • 7 ay önce

Qwen-Image-Edit-2511 is here! We’ve pushed the boundaries of consistency and control. A massive leap over the 2509 version, specifically built for real-world workflows. Model： 🤗 Hugging Face: 🧭 ModelScope:
1:25

Qwen-Image-Edit-2511 is here! We’ve pushed the boundaries of consistency and control. A massive leap over the 2509 version, specifically built for real-world workflows. Model： 🤗 Hugging Face: 🧭 ModelScope:

Tongyi Lab

42,276 görüntüleme • 6 ay önce

Qwen-Edit-2509-Multi-angle lighting LoRA Download link: Tongyi Lab
1:45

Qwen-Edit-2509-Multi-angle lighting LoRA Download link: Tongyi Lab

大雄

53,916 görüntüleme • 7 ay önce

Apple’s new LiTo model showcases a new method of converting 2D images to highly realistic 3D (Gaussian splat) objects More interestingly: it aims to accurately mimic the complex lighting, materials, and reflections shown in the original photo! They’re working to open source it
0:22

Apple’s new LiTo model showcases a new method of converting 2D images to highly realistic 3D (Gaussian splat) objects More interestingly: it aims to accurately mimic the complex lighting, materials, and reflections shown in the original photo! They’re working to open source it

Brad Lynch

40,615 görüntüleme • 3 ay önce

Today, we launch Viggle V4 + Character Refine. - Strong character consistency with precise motion control - Upload 1 image → auto-generate multi-angle references - 1:1 motion transfer from reference videos - Multi-character swap in complex scenes - Generate in SECONDS at lower cost - Up to 60s videos Powered by our proprietary 3D foundation model, built for speed, reliability, and full creative control. Try it for free! 👇
0:37

Today, we launch Viggle V4 + Character Refine. - Strong character consistency with precise motion control - Upload 1 image → auto-generate multi-angle references - 1:1 motion transfer from reference videos - Multi-character swap in complex scenes - Generate in SECONDS at lower cost - Up to 60s videos Powered by our proprietary 3D foundation model, built for speed, reliability, and full creative control. Try it for free! 👇

ViggleAI

400,268 görüntüleme • 3 ay önce

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!
1:03

3D AI is leveling up! Rodin 3D AI can create stunning, high-quality 3D models from just text or image inputs. And with its latest update, it can even generate 8K HDRI textures to bring your models to life. Check out the link in the comments!

el.cine

46,032 görüntüleme • 1 yıl önce

"#AI will never create clean meshes" AI 👇 This is the new #AI model from NVIDIA called Meshtron (jeez what a name 😅). It generates meshes of complex 3D objects closely resembling those created by professional artists. It opens the door to a more realistic generation of detailed 3D assets for animation, gaming, and virtual environments. The current version accepts the following control inputs: - Point cloud: Determines the shape of the output mesh. - Face count: Determines the density of the output mesh. - Quad ratio: Switches between quad and triangle tessellation. - Creativity: Can be adjusted to generate extra details in the model. Meshtron can either serve as a stand-alone remesher to improve the quality of existing models, or be used in tandem with a text-to-3D or image-to-3D model to generate artist-grade meshes from scratch.
0:26

"#AI will never create clean meshes" AI 👇 This is the new #AI model from NVIDIA called Meshtron (jeez what a name 😅). It generates meshes of complex 3D objects closely resembling those created by professional artists. It opens the door to a more realistic generation of detailed 3D assets for animation, gaming, and virtual environments. The current version accepts the following control inputs: - Point cloud: Determines the shape of the output mesh. - Face count: Determines the density of the output mesh. - Quad ratio: Switches between quad and triangle tessellation. - Creativity: Can be adjusted to generate extra details in the model. Meshtron can either serve as a stand-alone remesher to improve the quality of existing models, or be used in tandem with a text-to-3D or image-to-3D model to generate artist-grade meshes from scratch.

Gabriele Romagnoli

2,176,683 görüntüleme • 1 yıl önce