Loading video...

Video Failed to Load

Go Home

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.

wildmindai's profile picture

Wildminder

10,263 subscribers

23,398 views • 19 days ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Fast Byte Latent Transformer is accepted to ICML 2026! ⚡🥪 Byte-level LMs promise to free us from subword tokenizers, but decoding one byte at a time is super slow. We make BLT generation more efficient with BLT-D: text diffusion for parallel byte decoding. 1/
1:46

Fast Byte Latent Transformer is accepted to ICML 2026! ⚡🥪 Byte-level LMs promise to free us from subword tokenizers, but decoding one byte at a time is super slow. We make BLT generation more efficient with BLT-D: text diffusion for parallel byte decoding. 1/

Julie Kallini ✨

96,883 views • 1 month 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
0:42

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

26,976 views • 1 month ago

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:
1:08

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

37,247 views • 19 days ago

9 Key AI Concepts Explained in 7 minutes - Tokenization - Text Decoding - Prompt Engineering - Multi Step AI Agents - RAGs - RLHF - VAE - Diffusion Models - LoRA
6:35

9 Key AI Concepts Explained in 7 minutes - Tokenization - Text Decoding - Prompt Engineering - Multi Step AI Agents - RAGs - RLHF - VAE - Diffusion Models - LoRA

Bytebytego

98,387 views • 4 months ago

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)
0:48

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

668,441 views • 18 days ago

MotionStreamer announced on Hugging Face Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space
0:40

MotionStreamer announced on Hugging Face Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space

AK

43,387 views • 1 year ago

Speed and quality can finally coexist in diffusion-based language generation. Introducing DiDi-Instruct, a Discrete Diffusion Divergence Instruct method that distills a pre-trained discrete diffusion language model (dLLM) into a few-step student for ultra-fast generation. Built on integral KL-divergence minimization, DiDi-Instruct achieves up to 64× faster decoding, surpasses both its teacher and GPT-2, and cuts training time by 20×. Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct Paper: Code: Project: Our report: 📬 #PapersAccepted by Jiqizhixin
0:40

Speed and quality can finally coexist in diffusion-based language generation. Introducing DiDi-Instruct, a Discrete Diffusion Divergence Instruct method that distills a pre-trained discrete diffusion language model (dLLM) into a few-step student for ultra-fast generation. Built on integral KL-divergence minimization, DiDi-Instruct achieves up to 64× faster decoding, surpasses both its teacher and GPT-2, and cuts training time by 20×. Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct Paper: Code: Project: Our report: 📬 #PapersAccepted by Jiqizhixin

机器之心 JIQIZHIXIN

18,126 views • 7 months ago

Qwen 32B (4-bit) generates at &gt;40 toks/sec on an M4 Max with assisted decoding and Qwen 0.5B as the draft model. Coming soon to mlx-lm. Compare regular decoding (left) to assisted decoding (right):
0:23

Qwen 32B (4-bit) generates at &gt;40 toks/sec on an M4 Max with assisted decoding and Qwen 0.5B as the draft model. Coming soon to mlx-lm. Compare regular decoding (left) to assisted decoding (right):

Awni Hannun

50,353 views • 1 year ago

Dealing with data in Dart? 📉🎯 dart:convert makes it easy to handle common conversions like decoding UTF8 bytes, encoding/decoding JSON, and much more.
1:38

Dealing with data in Dart? 📉🎯 dart:convert makes it easy to handle common conversions like decoding UTF8 bytes, encoding/decoding JSON, and much more.

Flutter

11,570 views • 11 months ago

Unboxing the NVIDIA GeForce RTX 5090
1:03

Unboxing the NVIDIA GeForce RTX 5090

DaPoets

53,040 views • 1 year ago

MinerU-Diffusion A 2.5B diffusion-based OCR model that replaces slow autoregressive decoding with parallel block-wise diffusion, achieving up to 3.2x faster inference while improving robustness on complex documents with tables, formulas, and layouts.
0:22

MinerU-Diffusion A 2.5B diffusion-based OCR model that replaces slow autoregressive decoding with parallel block-wise diffusion, achieving up to 3.2x faster inference while improving robustness on complex documents with tables, formulas, and layouts.

DailyPapers

15,304 views • 2 months ago

The all-new R Λ Z Ξ R Blade 16: SLIMMER. SMARTER. SHARPER. 💻 Powered by up to an NVIDIA® GeForce RTX™ 5090 Laptop GPU for ultimate performance. Grab yours now at your nearest #RazerStore! 🔥
0:54

The all-new R Λ Z Ξ R Blade 16: SLIMMER. SMARTER. SHARPER. 💻 Powered by up to an NVIDIA® GeForce RTX™ 5090 Laptop GPU for ultimate performance. Grab yours now at your nearest #RazerStore! 🔥

RazerStore

25,675 views • 1 year ago

Geoscan 4 live decoding
0:36

Geoscan 4 live decoding

supertrack

24,091 views • 3 months ago

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:
1:36

try out the Gradio Demo for AudioLDM: Text-to-Audio Generation with Latent Diffusion Models on Hugging Face demo:

AK

82,137 views • 3 years ago

Experience Alan Wake 2 on GeForce RTX 50 Series with: 🟢NVIDIA DLSS 4 with Multi Frame Generation 🟢NVIDIA RTX Mega Geometry 🟢Ultra quality Ray Tracing preset Dive back into the darkness with #RTXOn
0:56

Experience Alan Wake 2 on GeForce RTX 50 Series with: 🟢NVIDIA DLSS 4 with Multi Frame Generation 🟢NVIDIA RTX Mega Geometry 🟢Ultra quality Ray Tracing preset Dive back into the darkness with #RTXOn

NVIDIA GeForce

162,897 views • 1 year ago

Latest update adds a new First Class environment, desk passthrough feature on Quest and lower decoding latency when streaming PCVR games at high bitrates on Quest 3, 3S &amp; Pico 4 Ultra. Enjoy!
0:34

Latest update adds a new First Class environment, desk passthrough feature on Quest and lower decoding latency when streaming PCVR games at high bitrates on Quest 3, 3S &amp; Pico 4 Ultra. Enjoy!

Guy Godin

36,153 views • 1 year ago

Marvel Rivals features DLSS 4 with Multi Frame Generation and NVIDIA Reflex, accelerating frame rates beyond 300 FPS for a fast and responsive experience on GeForce RTX 5060. Learn More:
1:05

Marvel Rivals features DLSS 4 with Multi Frame Generation and NVIDIA Reflex, accelerating frame rates beyond 300 FPS for a fast and responsive experience on GeForce RTX 5060. Learn More:

NVIDIA GeForce

46,608 views • 1 year ago

The NVIDIA GeForce RTX 5090 is the most powerful GeForce GPU ever made, bringing game-changing capabilities to gamers and creators. Jacob Freeman takes you through what's new on the GeForce RTX 5090 Founders Edition and RTX 50 features →
0:24

The NVIDIA GeForce RTX 5090 is the most powerful GeForce GPU ever made, bringing game-changing capabilities to gamers and creators. Jacob Freeman takes you through what's new on the GeForce RTX 5090 Founders Edition and RTX 50 features →

NVIDIA GeForce

65,146 views • 1 year ago

how fast is the RTX 5090? 🤔
0:27

how fast is the RTX 5090? 🤔

HYTE

37,243 views • 1 year ago