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.

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

AK

531,847 subscribers

17,592 views • 3 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

1 Comments

Jatin Garg3 days ago

pixel-space diffusion vs latent-space is the tradeoff everyone runs into. what did the 3B parameter budget go to — more denoising steps or better conditioning?

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

669,682 views • 4 months ago

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Meet Iris-3B: a pixel-space T2I model and general vision learner that generates every pixel directly. No VAE. Pre-trained from scratch, 3B, open weights. We also explore its generative prior on detail-critical vision tasks: depth estimation and image restoration. Fully open: weights, code and demo (Apache 2.0)

Speridlabs

80,397 views • 3 days ago

intensity, precision, conditioning and passion.. fine tuning the fine tuning 🤼‍♀️

intensity, precision, conditioning and passion.. fine tuning the fine tuning 🤼‍♀️

Nattie

55,627 views • 1 year 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:

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

37,906 views • 4 months ago

Map2World. turns text descriptions and sketch maps into full 3D worlds. -multi-diffusion in SLAT latent space for global consistency; - beaats SynCity - supports arbitrary world sizes.

Map2World. turns text descriptions and sketch maps into full 3D worlds. -multi-diffusion in SLAT latent space for global consistency; - beaats SynCity - supports arbitrary world sizes.

Wildminder

15,679 views • 5 months ago

Masako Yamada, our Senior Director, Quantum Applications, presents on the quantum edge in enterprise AI: how to unlock real-world outcomes with hybrid QML fine-tuning and beyond.

Masako Yamada, our Senior Director, Quantum Applications, presents on the quantum edge in enterprise AI: how to unlock real-world outcomes with hybrid QML fine-tuning and beyond.

IonQ

10,907 views • 5 months ago

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

We introduce W.A.L.T, a diffusion model for photorealistic video generation. Our model is a transformer trained on image and video generation in a shared latent space. 🧵👇

Agrim Gupta

431,358 views • 2 years ago

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

New short course on Fine-tuning LLMs! Many developers are moving beyond only prompting, to also fine-tuning LLMs - that is, taking a pre-trained model and training it further on your own data, which can deliver superior results inexpensively. In this course, Sharon Zhou, CEO of Lamini (disclosure: I’m a minor shareholder) shows you how to recognize when fine-tuning can be help, and how to train an open-source LLM on your own data. I hope you enjoy the course!

Andrew Ng

502,962 views • 3 years ago

Extremely proud of our recent "Lost in Latent Space" paper by our amazing PolymathicAI intern François Rozet ! How far do you think we can/should compress ? What is needed in the latent space to keep rolling out the physics right across so many scales?

Extremely proud of our recent "Lost in Latent Space" paper by our amazing PolymathicAI intern François Rozet ! How far do you think we can/should compress ? What is needed in the latent space to keep rolling out the physics right across so many scales?

Shirley Ho

51,275 views • 1 year ago

"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer" TL;DR: learns a continuous mesh latent space and generates vertices and connectivity in parallel with flow matching, producing quality 3D meshes up to 18× faster than autoregressive.

"MeshFlow: Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer" TL;DR: learns a continuous mesh latent space and generates vertices and connectivity in parallel with flow matching, producing quality 3D meshes up to 18× faster than autoregressive.

Alexandre Morgand

43,375 views • 4 months ago

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

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

AK

82,138 views • 3 years ago

Going above and beyond in training 😅

Going above and beyond in training 😅

Arsenal Women

63,796 views • 1 month ago

Meet Amazon Nova Forge, the easiest and most cost-effective path to your own frontier models. * Early Nova checkpoints across pre-training, mid-training, and post-training phases * Blend proprietary data with Amazon Nova-curated training data * Reinforcement Fine Tuning (RFT) with reward functions in your environment * Custom content moderation settings

Meet Amazon Nova Forge, the easiest and most cost-effective path to your own frontier models. * Early Nova checkpoints across pre-training, mid-training, and post-training phases * Blend proprietary data with Amazon Nova-curated training data * Reinforcement Fine Tuning (RFT) with reward functions in your environment * Custom content moderation settings

Amazon Web Services

2,344,168 views • 10 months ago

Sharing something exciting we've been working on as a Thanksgiving gift: Diffusion Self-Distillation (DSD), which redefines zero-shot customized image generation using FLUX. DSD is like DreamBooth, but zero-shot/training-free. It works across any input subject and desired context—character consistency, item/asset adaptation, scene relighting, and more. It even enables the creation of comics/mangas without any effort in fine-tuning or training a personalized model! 📰 Paper: 🌐 Website: Team effort with Eric Chan, Yunzhi Zhang, Leonidas Guibas, Jiajun Wu, and Gordon Wetzstein.

Sharing something exciting we've been working on as a Thanksgiving gift: Diffusion Self-Distillation (DSD), which redefines zero-shot customized image generation using FLUX. DSD is like DreamBooth, but zero-shot/training-free. It works across any input subject and desired context—character consistency, item/asset adaptation, scene relighting, and more. It even enables the creation of comics/mangas without any effort in fine-tuning or training a personalized model! 📰 Paper: 🌐 Website: Team effort with Eric Chan, Yunzhi Zhang, Leonidas Guibas, Jiajun Wu, and Gordon Wetzstein.

Prime (Shengqu) Cai

60,760 views • 1 year ago

Fine tuning the details with Coach Ledford. Tune into Wired:

Fine tuning the details with Coach Ledford. Tune into Wired:

Baltimore Ravens

44,380 views • 1 month ago

LLM post-training used to mean fine-tuning to a downstream task Robotics has been stuck in this setting, needing task-specific fine-tuning for best performance π07 changes this: It works out of the box & outperforms fine-tuned specialists Details:

LLM post-training used to mean fine-tuning to a downstream task Robotics has been stuck in this setting, needing task-specific fine-tuning for best performance π07 changes this: It works out of the box & outperforms fine-tuned specialists Details:

Chelsea Finn

77,108 views • 5 months ago

🚨 New Paper Training an LLM to speak low-resource language (EACL workshop, 2026) Tulu is spoken by 2M+ people in coastal Karnataka and LLMs basically can't speak it. We got to 85% grammar accuracy without fine-tuning anything or collecting a single new training example.

🚨 New Paper Training an LLM to speak low-resource language (EACL workshop, 2026) Tulu is spoken by 2M+ people in coastal Karnataka and LLMs basically can't speak it. We got to 85% grammar accuracy without fine-tuning anything or collecting a single new training example.

Lossfunk

121,229 views • 7 months ago

Designers can now ship UI directly. Vlad, our co-founder and designer, goes from Figma concept to AI fine-tuning in the live app using Cursor and Figma MCP. No more back and forth with engineers for a pixel-perfect result.

Designers can now ship UI directly. Vlad, our co-founder and designer, goes from Figma concept to AI fine-tuning in the live app using Cursor and Figma MCP. No more back and forth with engineers for a pixel-perfect result.

Alex Barashkov

37,878 views • 8 months ago