Loading video...

Video Failed to Load

Go Home

NVidia just released PiD: super resolution in pixel space directly from model latents 🔎 4X resolution for any generated image, FAST! 🏎️💨 FLUX.1, 2 and Z-Image (Qwen Image coming) of course, i built a demo: generate 4K images with Z-Image

multimodalart's profile picture

apolinario (poli)

15,745 subscribers

29,948 views • 1 month 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

🍌 Just released NanoBanana Pro LoRA Dataset Generator with fal Finally an easy way to create training datasets for: • Flux 2 • Z-Image • Qwen Image Edit • Any image-to-image model ✨ Uses Nano Banana Pro API on fal 🌐 100% browser-based - no server needed ⚡ Parallel generation for speed 🔗 Try it live: 💻 Code:
0:14

🍌 Just released NanoBanana Pro LoRA Dataset Generator with fal Finally an easy way to create training datasets for: • Flux 2 • Z-Image • Qwen Image Edit • Any image-to-image model ✨ Uses Nano Banana Pro API on fal 🌐 100% browser-based - no server needed ⚡ Parallel generation for speed 🔗 Try it live: 💻 Code:

Lovis Odin

30,072 views • 7 months ago

🆕 Image super-resolution model just dropped! Superior results even with a single sampling step. 🔥InvSR: Arbitrary-steps Image Super-resolution via Diffusion Inversion.
0:12

🆕 Image super-resolution model just dropped! Superior results even with a single sampling step. 🔥InvSR: Arbitrary-steps Image Super-resolution via Diffusion Inversion.

Gradio

53,331 views • 1 year ago

Step 1: Generate the base image with GPT-2 Step 2: Serve the image you just generated back to GPT-2 with this prompt: "Convert this scene into a 360 equirectangular image"
0:19

Step 1: Generate the base image with GPT-2 Step 2: Serve the image you just generated back to GPT-2 with this prompt: "Convert this scene into a 360 equirectangular image"

A.I.Warper

77,151 views • 2 months ago

NVIDIA just released a very impressive text-to-video paper. Video Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:
0:14

NVIDIA just released a very impressive text-to-video paper. Video Latent Diffusion Models (Video LDMs) use a diffusion model in a compressed latent space to generate high-resolution videos. Here's a brief overview of how it works: 1. Pre-train image LDM on a dataset of images. 2. Turn the image LDM into a Video LDM by adding temporal layers to model video frames. 3. Fine-tune the Video LDM on encoded video sequences to create a video generator. 4. Temporally align diffusion model upsamplers to generate high-resolution videos. 5. Validate Video LDM on real driving videos of 512x1024 resolution, achieving state-of-the-art performance. 6. Apply the approach in creative content creation with text-to-video modeling. Paper: Project:

Lior Alexander

158,553 views • 3 years ago

introducing Qwen. this new image model comes with great prompt understanding and text rendering. try it now for free in Krea Image.
0:19

introducing Qwen. this new image model comes with great prompt understanding and text rendering. try it now for free in Krea Image.

KREA AI

16,176 views • 11 months ago

You can now Remix your images 🎨 Click the Remix icon below your generated image and Venice will generate a similar image with some details and characteristics "remixed"
0:10

You can now Remix your images 🎨 Click the Remix icon below your generated image and Venice will generate a similar image with some details and characteristics "remixed"

Venice

14,923 views • 9 months ago

introducing Flux 2. this new model from BlackForestLabsAI - Unofficial supports up to 10 image inputs and works natively for image editing. try it now!
0:16

introducing Flux 2. this new model from BlackForestLabsAI - Unofficial supports up to 10 image inputs and works natively for image editing. try it now!

Krea

13,372 views • 7 months ago

1. Generate UI with gpt-image-2 2. Generate a normal map from the image 3. Dynamic lighting for UI components - raised elements actually cast shadows and get lit naturally.
0:13

1. Generate UI with gpt-image-2 2. Generate a normal map from the image 3. Dynamic lighting for UI components - raised elements actually cast shadows and get lit naturally.

Jacob Miller

57,059 views • 2 months ago

1 HOUR LEFT ⏰ Z-Image is now part of Cyber Monday! 70% OFF the entire Higgsfield Toolkit + all image models UNLIMITED for 365 days. Z-Image delivers insane realism, ultra-fast generation, and flawless bilingual text. FOLLOW & Retweet & reply - 265 credits in DM!
0:14

1 HOUR LEFT ⏰ Z-Image is now part of Cyber Monday! 70% OFF the entire Higgsfield Toolkit + all image models UNLIMITED for 365 days. Z-Image delivers insane realism, ultra-fast generation, and flawless bilingual text. FOLLOW & Retweet & reply - 265 credits in DM!

Higgsfield AI 🧩

462,120 views • 7 months ago

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.
0:18

Selected as a best paper finalist at #CVPR2026: PixelDiT from NVIDIA Research In most image generation models, a pretrained autoencoder compresses the image before any diffusion happens, causing quality loss that accumulates across the entire pipeline. PixelDiT, or Pixel Diffusion Transformers, removes this step entirely. It's a single-stage model that learns the diffusion process directly in pixel space, end-to-end.

NVIDIA AI

27,815 views • 29 days ago

I've been experimenting with embeddings a lot recently. Here's an interface I created that lets me interpolate between CLIP image embeddings and generate images from the intermediate latents Latent Surfing. it's kinda like a color picker, but for images. (1/n)
0:15

I've been experimenting with embeddings a lot recently. Here's an interface I created that lets me interpolate between CLIP image embeddings and generate images from the intermediate latents Latent Surfing. it's kinda like a color picker, but for images. (1/n)

aarya

122,731 views • 2 years ago

FLUX.2 is live on Runware! D0 drop! 🔥 Built by Black Forest Labs, FLUX.2 is the new SOTA model that brings better control over structure, text, and references in image generation. This is a huge step forward for image gen & image editing. And we’re here to offer you the best prices on D0. This model comes in three versions. Details below.
0:15

FLUX.2 is live on Runware! D0 drop! 🔥 Built by Black Forest Labs, FLUX.2 is the new SOTA model that brings better control over structure, text, and references in image generation. This is a huge step forward for image gen & image editing. And we’re here to offer you the best prices on D0. This model comes in three versions. Details below.

Runware

293,432 views • 7 months ago

from a single image, an entire video—preserving face (finally!), style, and mood. all generated on freepik. new flux model rocks.
0:15

from a single image, an entire video—preserving face (finally!), style, and mood. all generated on freepik. new flux model rocks.

Omar Pera

12,326 views • 1 year ago

A single image generated by GPT Image 2, combined with Seedance 2.0, can already achieve this kind of effect Below is the Image 2 prompt👇
0:15

A single image generated by GPT Image 2, combined with Seedance 2.0, can already achieve this kind of effect Below is the Image 2 prompt👇

Ai Arainz

28,468 views • 1 month ago

Yesss Jasper introduces LBM: Latent Bridge Matching for Fast Image-to-Image Translation💡 and drops an amazing ✨image relighting✨ demo that runs with a single(!) inference step 🔥
0:14

Yesss Jasper introduces LBM: Latent Bridge Matching for Fast Image-to-Image Translation💡 and drops an amazing ✨image relighting✨ demo that runs with a single(!) inference step 🔥

Linoy Tsaban

14,426 views • 1 year ago

🚀 Meet GLM-Image Edit — Z-AI's powerful image transformation model. ✨ Key features: 📝 Edit images with natural language prompts 📸 Upload up to 4 reference images 🧠 Preserve key elements & identity 🎯 Apply precise, controllable modifications 🖼️ High-quality, faithful image reimagining Describe the change. GLM-Image Edit does the rest. 🔥
0:15

🚀 Meet GLM-Image Edit — Z-AI's powerful image transformation model. ✨ Key features: 📝 Edit images with natural language prompts 📸 Upload up to 4 reference images 🧠 Preserve key elements & identity 🎯 Apply precise, controllable modifications 🖼️ High-quality, faithful image reimagining Describe the change. GLM-Image Edit does the rest. 🔥

WaveSpeedAI

15,060 views • 5 months ago

GPT Image 2.0 is now available on Akool 🚀 This isn’t just an upgrade—it’s a major leap in AI image generation. With GPT Image 2.0, you get: • Sharper, high-resolution outputs with improved detail and realism • Much stronger text rendering (finally, text in images that actually looks right) • Better prompt understanding for more accurate and controllable results • Improved consistency across variations and multi-image generations • More precise editing & refinement for iterative creative workflows Whether you're creating marketing visuals, product images, or storytelling assets, GPT Image 2.0 delivers cleaner, more reliable, and production-ready results. Now live on Akool, try the latest in AI image generation today.
0:10

GPT Image 2.0 is now available on Akool 🚀 This isn’t just an upgrade—it’s a major leap in AI image generation. With GPT Image 2.0, you get: • Sharper, high-resolution outputs with improved detail and realism • Much stronger text rendering (finally, text in images that actually looks right) • Better prompt understanding for more accurate and controllable results • Improved consistency across variations and multi-image generations • More precise editing & refinement for iterative creative workflows Whether you're creating marketing visuals, product images, or storytelling assets, GPT Image 2.0 delivers cleaner, more reliable, and production-ready results. Now live on Akool, try the latest in AI image generation today.

Akool Inc

1,541,129 views • 2 months ago

Figma is leveraging gpt-image-1 to generate and edit images from simple prompts, enabling designers to rapidly explore ideas and iterate visually directly in Figma.
0:15

Figma is leveraging gpt-image-1 to generate and edit images from simple prompts, enabling designers to rapidly explore ideas and iterate visually directly in Figma.

OpenAI Developers

183,475 views • 1 year ago

NVIDIA introduces Edify 3D AI model You can generate high quality 3D assets from text or image input under 2 minutes! With PBR materials, quad-mesh topologies, and 4k textures. 6 wild examples:
0:18

NVIDIA introduces Edify 3D AI model You can generate high quality 3D assets from text or image input under 2 minutes! With PBR materials, quad-mesh topologies, and 4k textures. 6 wild examples:

Min Choi

399,038 views • 1 year ago