Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Nvidia's PID (Pixel diffusion Decoder) It decodes latent representations into high-resolution images, replacing the decode–then–super-resolve cascade while achieving lower latency and higher visual quality page: HF repo:

Stable Diffusion Tutorials

8,772 subscribers

37,906 views • 5 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: 🧵(1/N)

The latent-vs-pixel debate misses the point. GPT Image 2 shows what users notice: pixel-level fidelity. Latent models show what scales: compact semantic structure. We connect them by replacing VAE/RAE decoders with a Pixel Diffusion Decoder. Code and Model available: 🧵(1/N)

Xuanchi Ren

669,706 views • 5 months ago

🚀 Pixel Diffusion Decoder (PiD) v1.5 is out 🎨 No color-shifting problem, better 4K visual quality 📦 Undistilled checkpoint and full training code 🧩 Support FLUX, FLUX2, Qwen-Image, Z-Image, ... Feel free to use it, reproduce it, and build on top of it 💻 Code: 🔗 Demo & comparison:

🚀 Pixel Diffusion Decoder (PiD) v1.5 is out 🎨 No color-shifting problem, better 4K visual quality 📦 Undistilled checkpoint and full training code 🧩 Support FLUX, FLUX2, Qwen-Image, Z-Image, ... Feel free to use it, reproduce it, and build on top of it 💻 Code: 🔗 Demo & comparison:

Xuanchi Ren

51,736 views • 3 months ago

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models turn the publicly available, state-of-the-art text-to-image LDM Stable Diffusion into an efficient and expressive text-to-video model with resolution up to 1280 x 2048 abs: project page:

AK

718,894 views • 3 years ago

FLUX.2 Klein in pure pixel space! No VAE. AsymFlow - hyper-realistic images by working directly in pixel space rather than using compressed latent representations. - sharper textures, superior visual fidelity - 40% faster - low-rank noise parameterization to solve high-dimensional bottlenecks ComfyUI support incoming

FLUX.2 Klein in pure pixel space! No VAE. AsymFlow - hyper-realistic images by working directly in pixel space rather than using compressed latent representations. - sharper textures, superior visual fidelity - 40% faster - low-rank noise parameterization to solve high-dimensional bottlenecks ComfyUI support incoming

Wildminder

27,210 views • 5 months ago

Awesome. NVIDIA dropped PiD - fast high-res latent decoding via pixel diffusion! - replace VAE - 4/8x upsampling - 2k decoding in <1s on RTX 5090 - works with FLUX.1/SD3/Z - rapid generation previews sharper details, much lower hardware lag compared to standard methods.

Awesome. NVIDIA dropped PiD - fast high-res latent decoding via pixel diffusion! - replace VAE - 4/8x upsampling - 2k decoding in <1s on RTX 5090 - works with FLUX.1/SD3/Z - rapid generation previews sharper details, much lower hardware lag compared to standard methods.

Wildminder

23,806 views • 5 months ago

How can we generate high-fidelity, complex 3D scenes? Quan Meng's LT3SD decomposes 3D scenes into latent tree representations, with diffusion on the latent trees enabling seamless infinite 3D scene synthesis! w/ Lei Li, Matthias Niessner

How can we generate high-fidelity, complex 3D scenes? Quan Meng's LT3SD decomposes 3D scenes into latent tree representations, with diffusion on the latent trees enabling seamless infinite 3D scene synthesis! w/ Lei Li, Matthias Niessner

Angela Dai

29,469 views • 2 years ago

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution paper page: Text-based diffusion models have exhibited remarkable success in generation and editing, showing great promise for enhancing visual content with their generative prior. However, applying these models to video super-resolution remains challenging due to the high demands for output fidelity and temporal consistency, which is complicated by the inherent randomness in diffusion models. Our study introduces Upscale-A-Video, a text-guided latent diffusion framework for video upscaling. This framework ensures temporal coherence through two key mechanisms: locally, it integrates temporal layers into U-Net and VAE-Decoder, maintaining consistency within short sequences; globally, without training, a flow-guided recurrent latent propagation module is introduced to enhance overall video stability by propagating and fusing latent across the entire sequences. Thanks to the diffusion paradigm, our model also offers greater flexibility by allowing text prompts to guide texture creation and adjustable noise levels to balance restoration and generation, enabling a trade-off between fidelity and quality. Extensive experiments show that Upscale-A-Video surpasses existing methods in both synthetic and real-world benchmarks, as well as in AI-generated videos, showcasing impressive visual realism and temporal consistency.

AK

32,849 views • 2 years ago

Scaling up GANs for Text-to-Image Synthesis present our 1B-parameter GigaGAN, achieving lower FID than Stable Diffusion v1.5, DALL·E 2, and Parti-750M. It generates 512px outputs at 0.13s, orders of magnitude faster than diffusion and autoregressive models, and inherits the disentangled, continuous, and controllable latent space of GANs abs: project page:

Scaling up GANs for Text-to-Image Synthesis present our 1B-parameter GigaGAN, achieving lower FID than Stable Diffusion v1.5, DALL·E 2, and Parti-750M. It generates 512px outputs at 0.13s, orders of magnitude faster than diffusion and autoregressive models, and inherits the disentangled, continuous, and controllable latent space of GANs abs: project page:

AK

278,220 views • 3 years ago

Iris-3B Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning paper:

Iris-3B Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning paper:

AK

20,060 views • 16 days ago

I just added 3D low-poly model generation to Retro Diffusion! Create super high quality low poly models with pixel art textures in minutes. Then animate them however you want with just a prompt! Check it out on the site and the API/MCP!

I just added 3D low-poly model generation to Retro Diffusion! Create super high quality low poly models with pixel art textures in minutes. Then animate them however you want with just a prompt! Check it out on the site and the API/MCP!

Astropulse

39,474 views • 1 month ago

Fixed resolution images in photoshop Make low resolution image high quality

Fixed resolution images in photoshop Make low resolution image high quality

Photoshop Tricks!

58,097 views • 1 year ago

Stream-DiffVSR: A low-latency, streamable video super-resolution model; - distills Stable Diffusion Upscaler to just 4 steps; - processes 720p ~3fps.

Stream-DiffVSR: A low-latency, streamable video super-resolution model; - distills Stable Diffusion Upscaler to just 4 steps; - processes 720p ~3fps.

Wildminder

16,196 views • 9 months ago

Don't let great ideas stay low resolution. With AKOOL's new Upscale feature, you can instantly enhance your AI-generated images with greater clarity, sharper details, and higher resolution output. From concept to production-ready quality in seconds. Because every pixel matters.

Don't let great ideas stay low resolution. With AKOOL's new Upscale feature, you can instantly enhance your AI-generated images with greater clarity, sharper details, and higher resolution output. From concept to production-ready quality in seconds. Because every pixel matters.

Akool Inc

2,509,281 views • 4 months ago

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Nvidia presents Edify 3D! The method can generate high-quality 3D assets from text descriptions. It uses a diffusion model to create detailed quad-mesh topologies and high-resolution textures in under 2 minutes.

Dreaming Tulpa 🥓👑

39,523 views • 1 year ago

Not every video starts in high resolution, but every video can end that way. 🎥 Video Super Resolution is in GA for NPU and CPU to help transform video quality using on-device AI to enhance lower-resolution footage.

Not every video starts in high resolution, but every video can end that way. 🎥 Video Super Resolution is in GA for NPU and CPU to help transform video quality using on-device AI to enhance lower-resolution footage.

Windows Developer

13,866 views • 2 months ago

Images, video, audio, actions — generative modeling has converged on one recipe: compress into continuous latents, generate in latent space, decode. Language is the lone exception: still generated token by token, as a long discrete stream. Latent Thought Flows: We compress 256 text tokens into 8 continuous latents, generate them with a one-step flow model, and read them out as text using an autoregressive decoder. Result: a better inference-compute vs. generation-quality Pareto frontier than a tuned autoregressive baseline — thanks to compression and one-step generation. Co-led w/ Zhengyang Geng 🧵

Images, video, audio, actions — generative modeling has converged on one recipe: compress into continuous latents, generate in latent space, decode. Language is the lone exception: still generated token by token, as a long discrete stream. Latent Thought Flows: We compress 256 text tokens into 8 continuous latents, generate them with a one-step flow model, and read them out as text using an autoregressive decoder. Result: a better inference-compute vs. generation-quality Pareto frontier than a tuned autoregressive baseline — thanks to compression and one-step generation. Co-led w/ Zhengyang Geng 🧵

Mihir Prabhudesai

83,020 views • 3 months ago

Diffusion models generate high-quality images but require hundreds of forward passes. MIT CSAIL and Adobe Research introduce Distribution Matching Distillation (DMD), a distillation approach that converts costly multi-step diffusion models into fast one-step generators. A thread 🧵

Diffusion models generate high-quality images but require hundreds of forward passes. MIT CSAIL and Adobe Research introduce Distribution Matching Distillation (DMD), a distillation approach that converts costly multi-step diffusion models into fast one-step generators. A thread 🧵

MIT CSAIL

34,383 views • 2 years ago

Reasoning = step-by-step thinking. Usually. Diffusion reasons in parallel and refines natively. Better quality without the latency tax. Samar Khanna on how diffusion reasoning works. We're hiring →

Reasoning = step-by-step thinking. Usually. Diffusion reasons in parallel and refines natively. Better quality without the latency tax. Samar Khanna on how diffusion reasoning works. We're hiring →

Inception

16,490 views • 6 months ago

WARNING 🚨 The BEST Fortnite Settings for BETTER Latency and FPS Fortnite is intentionally turning on high resolution to lower your frames and overall performance disc below, more tools, tips and much more

WARNING 🚨 The BEST Fortnite Settings for BETTER Latency and FPS Fortnite is intentionally turning on high resolution to lower your frames and overall performance disc below, more tools, tips and much more

Skiioh | PC Specialist 🔸

41,308 views • 10 days ago

🚨 BREAKING: A research lab just released a 15B model that generates multilingual talking human videos with synced audio, beats every competitor in human evaluation, and runs in 38 seconds on one GPU. It's called daVinci-MagiHuman. The key insight is that every other model in this category stacks cross-attention, multi-stream pipelines, and separate conditioning branches to handle video and audio together. This one throws all of that out and uses a single unified self-attention stream across all modalities. Super-resolution happens in latent space rather than pixel space so there's no extra VAE decode-encode round trip. The turbo VAE decoder cuts decoding overhead even further. The distilled version runs in 8 steps with no CFG at all. Visual quality, text alignment, and word error rate all beat Ovi 1.1 and LTX 2.3 on the benchmark table. 100% Opensource. Apache 2.0. Repo and research paper links are in the comments.

🚨 BREAKING: A research lab just released a 15B model that generates multilingual talking human videos with synced audio, beats every competitor in human evaluation, and runs in 38 seconds on one GPU. It's called daVinci-MagiHuman. The key insight is that every other model in this category stacks cross-attention, multi-stream pipelines, and separate conditioning branches to handle video and audio together. This one throws all of that out and uses a single unified self-attention stream across all modalities. Super-resolution happens in latent space rather than pixel space so there's no extra VAE decode-encode round trip. The turbo VAE decoder cuts decoding overhead even further. The distilled version runs in 8 steps with no CFG at all. Visual quality, text alignment, and word error rate all beat Ovi 1.1 and LTX 2.3 on the benchmark table. 100% Opensource. Apache 2.0. Repo and research paper links are in the comments.

Ihtesham Ali

45,723 views • 6 months ago