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.

Three new open-source models just landed in ComfyUI natively: → Gemma 4 (Google DeepMind) - multimodal LLM handling text, image, audio, and video input with built-in step-by-step reasoning mode → VOID (Netflix) - video object removal that also erases shadows, reflections, and physical interactions caused by the removed subject... show more

ComfyUI

49,055 subscribers

218,300 views • 1 month ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal. The highlights: → Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it → VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported → Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1 Learn more with our blog 👇

In May, we integrated 11 new models spanning image, 3D, audio, video, and multimodal. The highlights: → Krea 2 — style-first image generation, live as a Partner Node on day one. Competes on how the frame looks, not just what's in it → VOID (Netflix) — removes objects and everything they caused: shadows, reflections, physical interactions. Apache 2.0, natively supported → Tripo 3.1 + TripoSplat — one image to a full 3D Gaussian asset, end to end Also live in May: Gemma 4, HidDream-O1-Image, Stable Audio 3, BiRefNet, MoGe, Claude, OpenRouter, Luma UNI-1 Learn more with our blog 👇

ComfyUI

18,685 views • 25 days ago

Stable Diffusion Moment of Audio?? Ace-Step Audio Model just dropped and is now natively supported in ComfyUI. ACE-Step is an open-source music generation model jointly developed by ACE Studio and StepFun.

Stable Diffusion Moment of Audio?? Ace-Step Audio Model just dropped and is now natively supported in ComfyUI. ACE-Step is an open-source music generation model jointly developed by ACE Studio and StepFun.

ComfyUI

23,495 views • 1 year ago

NEW: Google releases Gemma 4, their most capable open models yet! 🤯 Apache-2.0, multimodal (text, image, and audio input), and multilingual (140 languages)! They can even run 100% locally in your browser on WebGPU. Watch it describe the Artemis II launch! 🚀 Try the demo! 👇

NEW: Google releases Gemma 4, their most capable open models yet! 🤯 Apache-2.0, multimodal (text, image, and audio input), and multilingual (140 languages)! They can even run 100% locally in your browser on WebGPU. Watch it describe the Artemis II launch! 🚀 Try the demo! 👇

Xenova

38,427 views • 2 months ago

🎉Generate. Edit. Repeat. All locally. Flux.1 Kontext [dev] is now open source and fully supported in ComfyUI! Everything below is now enabled: 👉Multi-Step Editing with Context 👉Character Consistency 👉Local Editing 👉Style Reference 👉Object / Background Removal 👉Multiple Inputs 👉Text Editing

🎉Generate. Edit. Repeat. All locally. Flux.1 Kontext [dev] is now open source and fully supported in ComfyUI! Everything below is now enabled: 👉Multi-Step Editing with Context 👉Character Consistency 👉Local Editing 👉Style Reference 👉Object / Background Removal 👉Multiple Inputs 👉Text Editing

ComfyUI

124,094 views • 1 year ago

Demis Hassabis on the next 12 Months: - Full multimodal convergence: Models like Gemini will seamlessly take in and output text, images, audio, and video, with cross-pollination that boosts reasoning + creativity. - Breakthrough visual intelligence: Image models like Nano Banana Pro will produce highly accurate infographics and show near-human visual understanding. - Language + video fusion: Video models integrated with LLMs unlock richer analysis, storytelling, and step-by-step visual reasoning. - World models go mainstream like Genie 3 - Agents become reliable

Demis Hassabis on the next 12 Months: - Full multimodal convergence: Models like Gemini will seamlessly take in and output text, images, audio, and video, with cross-pollination that boosts reasoning + creativity. - Breakthrough visual intelligence: Image models like Nano Banana Pro will produce highly accurate infographics and show near-human visual understanding. - Language + video fusion: Video models integrated with LLMs unlock richer analysis, storytelling, and step-by-step visual reasoning. - World models go mainstream like Genie 3 - Agents become reliable

Chubby♨️

89,236 views • 6 months ago

FLUX.2 [klein] 4B + 9B are the newest BFL models in the Flux family—combining image generation + image editing in one compact architecture. Built for interactive workflows and quick iteration, with extremely fast inference on distilled variants. Two models. Two modes. ⚡️

FLUX.2 [klein] 4B + 9B are the newest BFL models in the Flux family—combining image generation + image editing in one compact architecture. Built for interactive workflows and quick iteration, with extremely fast inference on distilled variants. Two models. Two modes. ⚡️

ComfyUI

19,899 views • 5 months ago

Mattes and Utilities Demo: VFX artist Doug Hogan breaks down a ComfyUI workflow that generates production-ready utility passes directly from your footage. No manual rotoscoping. No guesswork. What's inside: → Prompt-based background removal (RMBG) for fast, clean shots → SAM3 text-prompt segmentation for moving subjects → SAM3 point-based editor for precise matte control → Face segmentation for beauty and skin work in comp → Stable depth and normals passes for relighting and CG integration → App Mode - a simplified UI that hides the node graph entirely Everything ties back to your source plate's native resolution and frame rate automatically via get/set nodes. This is the kind of workflow that used to take a team. Now it runs in ComfyUI. Click the link below for the workflow 👇

Mattes and Utilities Demo: VFX artist Doug Hogan breaks down a ComfyUI workflow that generates production-ready utility passes directly from your footage. No manual rotoscoping. No guesswork. What's inside: → Prompt-based background removal (RMBG) for fast, clean shots → SAM3 text-prompt segmentation for moving subjects → SAM3 point-based editor for precise matte control → Face segmentation for beauty and skin work in comp → Stable depth and normals passes for relighting and CG integration → App Mode - a simplified UI that hides the node graph entirely Everything ties back to your source plate's native resolution and frame rate automatically via get/set nodes. This is the kind of workflow that used to take a team. Now it runs in ComfyUI. Click the link below for the workflow 👇

ComfyUI

26,631 views • 16 days ago

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️

The Segment Anything Model (SAM) by Meta AI is a step toward the first foundation model for image segmentation. SAM is capable of one-click segmentation of any object from photos or videos + zero-shot transfer to other segmentation tasks. Try the demo ➡️

AI at Meta

186,324 views • 3 years ago

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it!

Super excited to introduce Gemma 4 12B! 💎 - Multimodal: audio, image, video, and text input - Novel architecture: we removed the multimodal encoders for a unified, streamlined arch - New MacOS desktop app powered by LiteRT - MTP support Excited to see what you build with it!

Omar Sanseviero

125,135 views • 23 days ago

Wan2.1-VACE 14B & 1.3B are now natively supported in ComfyUI! This model from Wan brings all-in-one editing capability to your video generation: 🔹Text-to-Video & Image-to-Video 🔹 Video-to-video (Pose & depth control) 🔹 Inpainting & Outpainting 🔹 Character + object reference

Wan2.1-VACE 14B & 1.3B are now natively supported in ComfyUI! This model from Wan brings all-in-one editing capability to your video generation: 🔹Text-to-Video & Image-to-Video 🔹 Video-to-video (Pose & depth control) 🔹 Inpainting & Outpainting 🔹 Character + object reference

ComfyUI

21,517 views • 1 year ago

Track Anything: Segment Anything Meets Videos Track-Anything is a flexible and interactive tool for video object tracking and segmentation suitable for: - Video object tracking and segmentation with shot changes. - Visualized development and data annnotation for video object tracking and segmentation. - Object-centric downstream video tasks, such as video inpainting and editing. abs: github:

Track Anything: Segment Anything Meets Videos Track-Anything is a flexible and interactive tool for video object tracking and segmentation suitable for: - Video object tracking and segmentation with shot changes. - Visualized development and data annnotation for video object tracking and segmentation. - Object-centric downstream video tasks, such as video inpainting and editing. abs: github:

AK

578,577 views • 3 years ago

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

In Prompt Engineering for Vision Models, taught by Abby Jacques Verre and Caleb Kaiser of Comet , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for vision models could be text, point coordinates, or bounding boxes, depending on the model. You'll also learn to tune hyperparameters to shape the output. Models you'll use include Segment-Anything Model (SAM), OWL-ViT, and Stable Diffusion. You'll also learn to fine-tune Stable Diffusion to generate personalized images (say, an image of a specific person), using a handful of images for training. As an example of a multi-step workflow, you'll use OWL-ViT to detect an object based on a text prompt, then pass the bounding box to SAM to create a segmentation mask, and input that mask into Stable Diffusion to replace the original object with a new one based on a text prompt. Controlling vision models can be tricky; this course will teach prompting and fine-tuning techniques to get precise control over their output. Get started here:

Andrew Ng

151,198 views • 2 years ago

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

Friendly reminder that Google has an official app to run Gemma 4 on your phone. - 100% open source - Fully offline and private - Multimodal with text/audio/image - Works with Gemma E4B and E2B And the app is available on both iOS and Android. Steps and download below

Paul Couvert

724,656 views • 2 months ago

Introducing A Branding New ComfyUI Look and Native API Nodes! Seamlessly integrate 11 amazing online visual AI models into ComfyUI, including BlackForestLabsAI - Unofficial Flux, Hailuo AI-MiniMax Hub, , Kling AI, Luma, PixVerse, Recraft, Stability AI, Google Veo2, Ideogram, OpenAI GPT image-1, and Pika! 🔹One platform, 11 models, 65 nodes, all at once 🔹Chain the APIs with open models and workflows 🔹No hardware limitation!

Introducing A Branding New ComfyUI Look and Native API Nodes! Seamlessly integrate 11 amazing online visual AI models into ComfyUI, including BlackForestLabsAI - Unofficial Flux, Hailuo AI-MiniMax Hub, , Kling AI, Luma, PixVerse, Recraft, Stability AI, Google Veo2, Ideogram, OpenAI GPT image-1, and Pika! 🔹One platform, 11 models, 65 nodes, all at once 🔹Chain the APIs with open models and workflows 🔹No hardware limitation!

ComfyUI

187,242 views • 1 year ago

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.

LTX-2 is natively supported in ComfyUI on Day 0 🎬🔊 The next chapter in controllability for open-source video generation. - Open-source audio-video foundation model - Generates motion, dialogue, SFX, and music together - Canny, Depth & Pose video-to-video control - Keyframe-driven generation - Native upscaling and prompt enhancement Everything in a single pass.

ComfyUI

108,130 views • 5 months ago

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

TurboEdit Instant text-based image editing discuss: We address the challenges of precise image inversion and disentangled image editing in the context of few-step diffusion models. We introduce an encoder based iterative inversion technique. The inversion network is conditioned on the input image and the reconstructed image from the previous step, allowing for correction of the next reconstruction towards the input image. We demonstrate that disentangled controls can be easily achieved in the few-step diffusion model by conditioning on an (automatically generated) detailed text prompt. To manipulate the inverted image, we freeze the noise maps and modify one attribute in the text prompt (either manually or via instruction based editing driven by an LLM), resulting in the generation of a new image similar to the input image with only one attribute changed. It can further control the editing strength and accept instructive text prompt. Our approach facilitates realistic text-guided image edits in real-time, requiring only 8 number of functional evaluations (NFEs) in inversion (one-time cost) and 4 NFEs per edit. Our method is not only fast, but also significantly outperforms state-of-the-art multi-step diffusion editing techniques.

AK

16,062 views • 1 year ago

The first AI design agent with Nano Banana has dropped. It combines major models for image, video, and 3D asset generation all in one place. You can also edit the images, generate music, and even voiceovers! Step-by-step tutorial 👇

The first AI design agent with Nano Banana has dropped. It combines major models for image, video, and 3D asset generation all in one place. You can also edit the images, generate music, and even voiceovers! Step-by-step tutorial 👇

Alvaro Cintas

158,854 views • 9 months ago

ComfyUI MCP server - A project from Pixelle AI Shoutout to Pixelle-MCP - an amazing open-source project that bridges ComfyUI with LLMs through the MCP protocol. Zero-code, talk to your LLM to iterate ComfyUI workflow! Highlights: - Full TISV (Text, Image, Sound/Speech, Video) support - Flexible deployment options - Easy setup with Docker or one-click scripts - Custom workflow tools in just a few steps 🧵👇

ComfyUI MCP server - A project from Pixelle AI Shoutout to Pixelle-MCP - an amazing open-source project that bridges ComfyUI with LLMs through the MCP protocol. Zero-code, talk to your LLM to iterate ComfyUI workflow! Highlights: - Full TISV (Text, Image, Sound/Speech, Video) support - Flexible deployment options - Easy setup with Docker or one-click scripts - Custom workflow tools in just a few steps 🧵👇

ComfyUI

27,873 views • 10 months ago

Object Cutter Create high-quality HD background removal for ANY object in your image with a text prompt or bounding boxes!

Object Cutter Create high-quality HD background removal for ANY object in your image with a text prompt or bounding boxes!

Gradio

135,968 views • 1 year ago

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.

Tracking Anything with Decoupled Video Segmentation paper page: Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation.

AK

305,560 views • 2 years ago