正在加载视频...

视频加载失败

返回首页

Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization 🤯 Colab 🥳 Thanks to Tao Yang ❤ Peiran Ren ❤ Xuansong Xie ❤ Lei Zhang ❤ 🎅⛄🎄🎁 Happy Holidays! 🎅⛄🎄🎁 📄paper: 🧬code: 🦒colab by please try it 🐣

camenduru's profile picture

camenduru

21,278 subscribers

50,518 次观看 • 2 年前 •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

10 条评论

camenduru 的头像
camenduru2 年前

I found this 📄 paper on 📬 Thanks to @AutoVisionGroup ❤

Crystalwizard 的头像
Crystalwizard2 年前

@thibaudz @emmanuel_2m

Noah Thi Ha Win (✸,✸) 的头像
Noah Thi Ha Win (✸,✸)2 年前

Thanks you for sharing @camenduru 🥰

wwwwg 的头像
wwwwg2 年前

@memdotai mem it

haareblond 的头像
haareblond2 年前

So its stable diffusion bit in pixel space?

Suyog 的头像
Suyog2 年前

@_akhaliq Is there a comparison to other super resolution methods?

Saied 的头像
Saied2 年前

Non-commercial

Dhananjay Kumar 的头像
Dhananjay Kumar2 年前

How is this different from Codeformer?

Runs 的头像
Runs2 年前

Really cool. How could one use this to achieve similar results as Magnific, where it's more "opinionated" than a simple upscale?

Sebastian G 的头像
Sebastian G2 年前

@memdotai #upscale #cityscapes #superresolution

相关视频

DemoFusion: Democratising High-Resolution Image Generation With No $$$ 🖼 Img2Img Colab 🥳 Thanks to Ruoyi Du ❤ Dongliang Chang ❤ Timothy Hospedales ❤ Yi-Zhe Song ❤ Zhanyu Ma ❤ 🌐page: 📄paper: 🧬code: 🦒colab by please try it 🐣
0:37

DemoFusion: Democratising High-Resolution Image Generation With No $$$ 🖼 Img2Img Colab 🥳 Thanks to Ruoyi Du ❤ Dongliang Chang ❤ Timothy Hospedales ❤ Yi-Zhe Song ❤ Zhanyu Ma ❤ 🌐page: 📄paper: 🧬code: 🦒colab by please try it 🐣

camenduru

52,025 次观看 • 2 年前

HierSpeech++: Zero-shot Speech Synthesis 🎙 Voice-Clone Colab 🥳 Thanks to Sang-Hoon Lee ❤ Ha-Yeong Choi ❤ Seung-Bin Kim ❤ Seong-Whan Lee ❤ 🌐page: 📄paper: 🧬code: 🦒colab by please try it 🐣
0:29

HierSpeech++: Zero-shot Speech Synthesis 🎙 Voice-Clone Colab 🥳 Thanks to Sang-Hoon Lee ❤ Ha-Yeong Choi ❤ Seung-Bin Kim ❤ Seong-Whan Lee ❤ 🌐page: 📄paper: 🧬code: 🦒colab by please try it 🐣

camenduru

46,010 次观看 • 2 年前

It's kind of real-time 😋 (Free T4 🦄 Colab) Thanks to Allen (Simian) Luo (LCM) ❤ Lykon (Base Model) ❤ Ollin Boer Bohan (Tiny AutoEncoder) ❤ Radamés Ajna (UI) ❤ 🦒colab: please try it 🐣
0:43

It's kind of real-time 😋 (Free T4 🦄 Colab) Thanks to Allen (Simian) Luo (LCM) ❤ Lykon (Base Model) ❤ Ollin Boer Bohan (Tiny AutoEncoder) ❤ Radamés Ajna (UI) ❤ 🦒colab: please try it 🐣

camenduru

10,947 次观看 • 2 年前

🎥😳 Identity-Preserving Text-to-Video Generation by Frequency Decomposition 🔥 Jupyter Notebook, Tost AI, @runpod_io 🥳 Thanks to Shenghai Yuan ❤ Jinfa Huang ❤ Xianyi He ❤ Yunyuan Ge ❤ Yujun Shi ❤ Liuhan Chen ❤ Jiebo Luo ❤ Li Yuan ❤ 🌐page: 🧬code: 📄paper: 🍇runpod: 🍊jupyter by 🥪tost: please try it 🐣
1:06

🎥😳 Identity-Preserving Text-to-Video Generation by Frequency Decomposition 🔥 Jupyter Notebook, Tost AI, @runpod_io 🥳 Thanks to Shenghai Yuan ❤ Jinfa Huang ❤ Xianyi He ❤ Yunyuan Ge ❤ Yujun Shi ❤ Liuhan Chen ❤ Jiebo Luo ❤ Li Yuan ❤ 🌐page: 🧬code: 📄paper: 🍇runpod: 🍊jupyter by 🥪tost: please try it 🐣

camenduru

27,089 次观看 • 1 年前

🎞 ToonCrafter: Generative cartoon interpolation 🤯 Jupyter Notebook 🥳 Thanks to ToonCrafter Team ❤ 🧬code: 🍊jupyter by please try it 🐣
1:07

🎞 ToonCrafter: Generative cartoon interpolation 🤯 Jupyter Notebook 🥳 Thanks to ToonCrafter Team ❤ 🧬code: 🍊jupyter by please try it 🐣

camenduru

55,867 次观看 • 2 年前

💃 StableAnimator: High-Quality Identity-Preserving Human Image Animation 🕺 template with Gradio 🥳 Thanks to Shuyuan Tu ❤ Zhen Xing ❤ Xintong Han ❤ Zhi-Qi Cheng ❤ Qi Dai ❤ Chong Luo ❤ Zuxuan Wu ❤ 🌐page: 🧬code: 📄paper: 🍇runpod template by
1:20

💃 StableAnimator: High-Quality Identity-Preserving Human Image Animation 🕺 template with Gradio 🥳 Thanks to Shuyuan Tu ❤ Zhen Xing ❤ Xintong Han ❤ Zhi-Qi Cheng ❤ Qi Dai ❤ Chong Luo ❤ Zuxuan Wu ❤ 🌐page: 🧬code: 📄paper: 🍇runpod template by

camenduru

30,090 次观看 • 1 年前

🎙️ FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait 👄 Jupyter Notebook 🥳 Thanks to Taekyung Ki ❤ DongchanMin ❤ Gyeongsu Chae ❤ Thanks to Baku ❤ for the tutorial. 🌐page: 🧬code: 📄paper: 🍊jupyter:
1:04

🎙️ FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait 👄 Jupyter Notebook 🥳 Thanks to Taekyung Ki ❤ DongchanMin ❤ Gyeongsu Chae ❤ Thanks to Baku ❤ for the tutorial. 🌐page: 🧬code: 📄paper: 🍊jupyter:

camenduru

12,363 次观看 • 10 个月前

🎙 Apache-2.0 🔥 OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation Thanks to Qijun Gan ❤ Ruizi Yang ❤ Jianke Zhu ❤ Shaofei Xue ❤ Steven Hoi ❤ 🌐page: 🧬code: 📄paper:
0:20

🎙 Apache-2.0 🔥 OmniAvatar: Efficient Audio-Driven Avatar Video Generation with Adaptive Body Animation Thanks to Qijun Gan ❤ Ruizi Yang ❤ Jianke Zhu ❤ Shaofei Xue ❤ Steven Hoi ❤ 🌐page: 🧬code: 📄paper:

camenduru

12,959 次观看 • 10 个月前

🚧 We are working on StyleTTS2 model training. 🏗 I think it's time to show some results from the training... 🔥 The model license is the same as the repo (MIT) 🎙 StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models 🔥 Jupyter Notebook 🥳 Thanks to Yinghao Aaron Li ❤ Cong Han ❤ Vinay S Raghavan ❤ Gavin Mischler ❤ Nima Mesgarani ❤ 📄paper: 🧬code: 🗃dataset: 📦model: please try it 🐣
1:15

🚧 We are working on StyleTTS2 model training. 🏗 I think it's time to show some results from the training... 🔥 The model license is the same as the repo (MIT) 🎙 StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models 🔥 Jupyter Notebook 🥳 Thanks to Yinghao Aaron Li ❤ Cong Han ❤ Vinay S Raghavan ❤ Gavin Mischler ❤ Nima Mesgarani ❤ 📄paper: 🧬code: 🗃dataset: 📦model: please try it 🐣

camenduru

11,532 次观看 • 2 年前

🖼 Advanced Live Portrait 🔥 Jupyter Notebook + Tost AI + + ComfyUI 🥳 Thanks to Live Portrait Team ❤ github/PowerHouseMan ❤ 🧬code: 🍇runpod: 🗺workflow: 🍊jupyter: 🥪tost: please try it 🐣
1:42

🖼 Advanced Live Portrait 🔥 Jupyter Notebook + Tost AI + + ComfyUI 🥳 Thanks to Live Portrait Team ❤ github/PowerHouseMan ❤ 🧬code: 🍇runpod: 🗺workflow: 🍊jupyter: 🥪tost: please try it 🐣

camenduru

50,816 次观看 • 1 年前

🔥 Clarity-Upscaler: Open-Source 🔥 Open-Source 🔥 Open-Source 🚒 Upscaler 🥳 Thanks to @philipp1337x ❤ 🌐page: 🧬code: 🕸replicate: please try it 🐣
1:37

🔥 Clarity-Upscaler: Open-Source 🔥 Open-Source 🔥 Open-Source 🚒 Upscaler 🥳 Thanks to @philipp1337x ❤ 🌐page: 🧬code: 🕸replicate: please try it 🐣

camenduru

18,799 次观看 • 2 年前

📺 HunyuanVideo: A Systematic Framework For Large Video Generative Models is now available on Tost AI and @runpod_io 🥳 Thanks to toad Team ❤ 🌐page: 🧬code: 🍇runpod: 🥪tost: please try it 🐣
1:07

📺 HunyuanVideo: A Systematic Framework For Large Video Generative Models is now available on Tost AI and @runpod_io 🥳 Thanks to toad Team ❤ 🌐page: 🧬code: 🍇runpod: 🥪tost: please try it 🐣

camenduru

18,502 次观看 • 1 年前

Merry Christmas and Happy New Year 2026 🎂🎀🎄🎊 May God’s love always be with you and🎅your family 🎀🎁🎅🎉🎈🎄🎊⛄🎶🍰 🎂🎶⛄🎊🎄🎈🎁🎀🎉❄
0:59

Merry Christmas and Happy New Year 2026 🎂🎀🎄🎊 May God’s love always be with you and🎅your family 🎀🎁🎅🎉🎈🎄🎊⛄🎶🍰 🎂🎶⛄🎊🎄🎈🎁🎀🎉❄

🕊🌹L♥VE_SIYA🌹🕊

15,198 次观看 • 5 个月前

🎥🤯 LTVX the first Real-time AI video generation open source model 🔥🔥🔥🚒 Jupyter Notebook, Tost AI, @runpod_io and ComfyUI 🥳 Thanks to Lightricks Team ❤ 🌐page: 🧬code: 🍇runpod: 🗺workflow: 🍊jupyter by 🥪tost: please try it 🐣
0:53

🎥🤯 LTVX the first Real-time AI video generation open source model 🔥🔥🔥🚒 Jupyter Notebook, Tost AI, @runpod_io and ComfyUI 🥳 Thanks to Lightricks Team ❤ 🌐page: 🧬code: 🍇runpod: 🗺workflow: 🍊jupyter by 🥪tost: please try it 🐣

camenduru

16,751 次观看 • 1 年前

🌲 Black Forest Labs: FLUX.1 Fill Outpainting 🔥 Jupyter Notebook, Tost AI, @runpod_io and ComfyUI 🥳 Thanks to Black Forest Labs Team ❤ 🌐page: 🧬code: 🍇runpod: 🗺workflow: 🍊jupyter: 🥪tost: please try it 🐣
0:37

🌲 Black Forest Labs: FLUX.1 Fill Outpainting 🔥 Jupyter Notebook, Tost AI, @runpod_io and ComfyUI 🥳 Thanks to Black Forest Labs Team ❤ 🌐page: 🧬code: 🍇runpod: 🗺workflow: 🍊jupyter: 🥪tost: please try it 🐣

camenduru

15,334 次观看 • 1 年前

🕹️ HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels 🌌 Jupyter Notebook 🥳 I added quantization to HunyuanWorld 1.0, and it now runs with 24GB of VRAM 🥳 Thanks to Tencent Hunyuan - HunyuanWorld Team ❤ 🧬code: 🧬quant-code: 📄paper: 🌐page: 🍊jupyter:
1:17

🕹️ HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels 🌌 Jupyter Notebook 🥳 I added quantization to HunyuanWorld 1.0, and it now runs with 24GB of VRAM 🥳 Thanks to Tencent Hunyuan - HunyuanWorld Team ❤ 🧬code: 🧬quant-code: 📄paper: 🌐page: 🍊jupyter:

camenduru

35,402 次观看 • 10 个月前

🔥FLUX.2-klein-4B pure C implementation now runs on Windows (AMD + Intel) 🥳 Thanks to Black Forest Labs ❤ antirez ❤ and MiniMax (official) ❤ 🧬 🎮
2:10

🔥FLUX.2-klein-4B pure C implementation now runs on Windows (AMD + Intel) 🥳 Thanks to Black Forest Labs ❤ antirez ❤ and MiniMax (official) ❤ 🧬 🎮

camenduru

14,917 次观看 • 4 个月前

🎅🎄🎅🎄🎅🎄 Happy Holidays 〜
1:31

🎅🎄🎅🎄🎅🎄 Happy Holidays 〜

高野 寛 🍥

22,288 次观看 • 5 个月前

🎧 Dia is a 1.6B parameter text to speech model created by Nari Labs. (Apache 2.0) 🔊 Jupyter Notebook 🥳 Thanks to Toby Kim ❤ Nari Labs ❤ 🌐page: 🧬code: 🍊jupyte:
2:00

🎧 Dia is a 1.6B parameter text to speech model created by Nari Labs. (Apache 2.0) 🔊 Jupyter Notebook 🥳 Thanks to Toby Kim ❤ Nari Labs ❤ 🌐page: 🧬code: 🍊jupyte:

camenduru

11,335 次观看 • 1 年前

🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 It‘s ways too early to get back to work today or for any closer contact to reality - if you ask me. So why not take this fairytale train crawling slowly through the winter scenery ? 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂
1:04

🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 It‘s ways too early to get back to work today or for any closer contact to reality - if you ask me. So why not take this fairytale train crawling slowly through the winter scenery ? 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂 🎅🎄🎁🌟☃️🚂

The Cult Cat

23,673 次观看 • 1 年前