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.

Visual annotation with Ray3 unlocks precise control for visual direction. Scribble on the frame to guide subjects to attack or befriend each other. Each stroke evokes intent for spatial blocking, going beyond the limits of text prompts. Try Ray3 in Dream Machine.

Luma

197,585 subscribers

471,970 views • 9 months ago •via X (Twitter)

Science & Technology Education Arts

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Visual annotation with Ray3 enables precision for scene entry. Sketch motion cues for how elements emerge into frame. Define approach paths or reveal appearances. Direct in off-screen surprises with more than just text prompts. Try Ray3 in Dream Machine.

Visual annotation with Ray3 enables precision for scene entry. Sketch motion cues for how elements emerge into frame. Define approach paths or reveal appearances. Direct in off-screen surprises with more than just text prompts. Try Ray3 in Dream Machine.

Luma

374,817 views • 9 months ago

Ray2 Keyframes, Extend & Loop is now here. Create your visual story with precise frame-by-frame control, seamless transitions, spatial exploration and long-form video durations using #Ray2 Text-to-Video and Image-to-Video models in Dream Machine.

Ray2 Keyframes, Extend & Loop is now here. Create your visual story with precise frame-by-frame control, seamless transitions, spatial exploration and long-form video durations using #Ray2 Text-to-Video and Image-to-Video models in Dream Machine.

Luma

7,362,289 views • 1 year ago

This is Ray3. The world’s first reasoning video model, and the first to generate studio-grade HDR. Now with an all-new Draft Mode for rapid iteration in creative workflows, and state of the art physics and consistency. Available now for free in Dream Machine.

This is Ray3. The world’s first reasoning video model, and the first to generate studio-grade HDR. Now with an all-new Draft Mode for rapid iteration in creative workflows, and state of the art physics and consistency. Available now for free in Dream Machine.

Luma

8,603,921 views • 10 months ago

Wan2.6: Commercial-Grade Image Output Wan2.6-Image is now available. 🖼️ Interleaved Text-and-Image Output：Generate interleaved text-and-image content with logical reasoning capabilities — enabling layered, narrative-driven visual storytelling. 🖼️ Multi-Image Conditioned Generation：Support flexible referencing, combining, and replacement of multiple images, integrating varied visual inspirations to generate novel and compelling results 🖼️ Commercial-Grade ID Preservation：High consistency in characters, styles, and elements for commercial scenarios. 🖼️ Extract creative elements — such as color, style, and composition — from reference images to enable aesthetically driven image generation. 🖼️ Precise Control of Camera Angles and Lighting：Support specifying camera perspective, spatial depth (foreground/background), and lighting details — enabling precise control over spatial composition and atmospheric mood. Try Wan2.6 today.

Wan2.6: Commercial-Grade Image Output Wan2.6-Image is now available. 🖼️ Interleaved Text-and-Image Output：Generate interleaved text-and-image content with logical reasoning capabilities — enabling layered, narrative-driven visual storytelling. 🖼️ Multi-Image Conditioned Generation：Support flexible referencing, combining, and replacement of multiple images, integrating varied visual inspirations to generate novel and compelling results 🖼️ Commercial-Grade ID Preservation：High consistency in characters, styles, and elements for commercial scenarios. 🖼️ Extract creative elements — such as color, style, and composition — from reference images to enable aesthetically driven image generation. 🖼️ Precise Control of Camera Angles and Lighting：Support specifying camera perspective, spatial depth (foreground/background), and lighting details — enabling precise control over spatial composition and atmospheric mood. Try Wan2.6 today.

Wan

33,264 views • 6 months ago

🧵MSNBC host Katy Tur's opening thoughts Thursday on yesterday's assassination of Charlie Kirk: "Today is a -- sigh -- terrible day. Almost 24 hours ago, down to the minute we learned that Charlie Kirk had been shot and as president trump posted at 440pm, he learned that Kirk had been killed in that attack. It was an attack on a man, but it was also an attack on the foundation of this country, on the idea that we are able to talk to each other, disagree with each other, debate each other, yell at each other, even we don't physically harm each other. We don't murder each other. We certainly don't justify it or make excuses for it."

🧵MSNBC host Katy Tur's opening thoughts Thursday on yesterday's assassination of Charlie Kirk: "Today is a -- sigh -- terrible day. Almost 24 hours ago, down to the minute we learned that Charlie Kirk had been shot and as president trump posted at 440pm, he learned that Kirk had been killed in that attack. It was an attack on a man, but it was also an attack on the foundation of this country, on the idea that we are able to talk to each other, disagree with each other, debate each other, yell at each other, even we don't physically harm each other. We don't murder each other. We certainly don't justify it or make excuses for it."

Curtis Houck

1,189,928 views • 10 months ago

Resolution games did a pretty great job on the visual details in Retrocade Not only do the games have screen reflections emitting onto the control decks when the lighting is dark They also added subpixel shaders for each machine, depending on the display technology used

Resolution games did a pretty great job on the visual details in Retrocade Not only do the games have screen reflections emitting onto the control decks when the lighting is dark They also added subpixel shaders for each machine, depending on the display technology used

Brad Lynch

24,610 views • 5 months ago

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation paper page: Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prompts and specified durations. However, using a single text prompt as input lacks the fine-grained control needed by animators, such as composing multiple actions and defining precise durations for parts of the motion. To address this, we introduce the new problem of timeline control for text-driven motion synthesis, which provides an intuitive, yet fine-grained, input interface for users. Instead of a single prompt, users can specify a multi-track timeline of multiple prompts organized in temporal intervals that may overlap. This enables specifying the exact timings of each action and composing multiple actions in sequence or at overlapping intervals. To generate composite animations from a multi-track timeline, we propose a new test-time denoising method. This method can be integrated with any pre-trained motion diffusion model to synthesize realistic motions that accurately reflect the timeline. At every step of denoising, our method processes each timeline interval (text prompt) individually, subsequently aggregating the predictions with consideration for the specific body parts engaged in each action. Experimental comparisons and ablations validate that our method produces realistic motions that respect the semantics and timing of given text prompts.

AK

126,585 views • 2 years ago

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,769 views • 10 months ago

One of the biggest area I’m working on right now is trying to bridge the gap between linear chat interfaces and the non-linear nature of human thinking. Benji Taylor’s Agentation already shows that markup and annotation resonate strongly with visual feedback, and I’ve found they feel more natural in text-based environments as well. One tiny step, but in the right direction. Coming tonight to

One of the biggest area I’m working on right now is trying to bridge the gap between linear chat interfaces and the non-linear nature of human thinking. Benji Taylor’s Agentation already shows that markup and annotation resonate strongly with visual feedback, and I’ve found they feel more natural in text-based environments as well. One tiny step, but in the right direction. Coming tonight to

Balint Orosz

41,183 views • 4 months ago

This is one of my biggest concern… now it’s spread beyond the USA. Who sold us the idea we are not good for each other? How did they convince us to hate each other so much, the common thought of being with each is repulsive. We need to THINK

This is one of my biggest concern… now it’s spread beyond the USA. Who sold us the idea we are not good for each other? How did they convince us to hate each other so much, the common thought of being with each is repulsive. We need to THINK

Dr. God Abeg ooo

147,961 views • 10 months ago

Natalie Portman: “What’s going on in our country right now is absolutely horrific with what the federal government, Trump’s government, Kristi Noem, ICE, what they’re doing is really the worst of the worst of humanity. We also have the best of the best of humanity for the way people are showing up for each other in community, and Americans coming out to support each other and protect each other and fight against injustice”

Natalie Portman: “What’s going on in our country right now is absolutely horrific with what the federal government, Trump’s government, Kristi Noem, ICE, what they’re doing is really the worst of the worst of humanity. We also have the best of the best of humanity for the way people are showing up for each other in community, and Americans coming out to support each other and protect each other and fight against injustice”

Marco Foster

571,397 views • 5 months ago

The President of the United States is supposed to try and make life better for everyone. Not attack people based on where they live or who they voted for. Not fuel the flames of hatred and division. Not do everything they can to pit everyone against each other. What's happening right now isn't normal.

The President of the United States is supposed to try and make life better for everyone. Not attack people based on where they live or who they voted for. Not fuel the flames of hatred and division. Not do everything they can to pit everyone against each other. What's happening right now isn't normal.

Kelly Morrison

66,913 views • 9 months ago

When planes fly in close proximity (within visual range, typically on similar airways or crossing paths), pilots sometimes chat with each other on a common radio frequency, such as 121.5 MHz (the international emergency frequency) or 123.45 MHz, which is often informally referred to as the "air-to-air" or "chat" frequency especially over the ocean or remote areas.

When planes fly in close proximity (within visual range, typically on similar airways or crossing paths), pilots sometimes chat with each other on a common radio frequency, such as 121.5 MHz (the international emergency frequency) or 123.45 MHz, which is often informally referred to as the "air-to-air" or "chat" frequency especially over the ocean or remote areas.

Aviation

745,035 views • 8 months ago

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:

Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:

Avthar

10,723 views • 3 months ago

Victor Gao: ‘When China🇨🇳 got involved between Iran and Saudi Arabia🇸🇦, you got PEACE. When the US🇺🇸 and Israel got involved…you get hostility, WAR, confrontation, DESTRUCTION. So the choice is very obvious for Middle Eastern countries. I hope when the dust settles after this war of aggression against Iran, the Iranians and the Arabs will shake hand again, preferably with Chinese intervention and mediation and they may cement their friendship and cooperation for decades and centuries to come. Because it will be suicidal for the Sunni Arabs and Shiite Iranians to be at each other’s jugular. It will be much better if they can recognise each other, respect each other, shake each other’s hand and engage in cooperation with each other rather than as some other countries are leading them in the wrong direction, being hostile with each other, trying to destroy each other, get to each other’s jugular. That will not be a better Muslim world at large.’ —Victor Gao, President of the Center for China and Globalisation, on the latest episode of Going Underground Watch the full interview in the quoted post below👇

Victor Gao: ‘When China🇨🇳 got involved between Iran and Saudi Arabia🇸🇦, you got PEACE. When the US🇺🇸 and Israel got involved…you get hostility, WAR, confrontation, DESTRUCTION. So the choice is very obvious for Middle Eastern countries. I hope when the dust settles after this war of aggression against Iran, the Iranians and the Arabs will shake hand again, preferably with Chinese intervention and mediation and they may cement their friendship and cooperation for decades and centuries to come. Because it will be suicidal for the Sunni Arabs and Shiite Iranians to be at each other’s jugular. It will be much better if they can recognise each other, respect each other, shake each other’s hand and engage in cooperation with each other rather than as some other countries are leading them in the wrong direction, being hostile with each other, trying to destroy each other, get to each other’s jugular. That will not be a better Muslim world at large.’ —Victor Gao, President of the Center for China and Globalisation, on the latest episode of Going Underground Watch the full interview in the quoted post below👇

Going Underground

48,948 views • 2 months ago

🚔 The inmates are running the asylum in Minneapolis From turning on each other over mistaken license plate tracking (and attacking each other with projectile adult objects) to wine mom meltdowns in yoga studios.. things are not going well for the anti-ICE keystone cops.

🚔 The inmates are running the asylum in Minneapolis From turning on each other over mistaken license plate tracking (and attacking each other with projectile adult objects) to wine mom meltdowns in yoga studios.. things are not going well for the anti-ICE keystone cops.

10 Minute Drill

38,097 views • 5 months ago

Today is a very emotional day. 💕 I am headed to NYC with Adeline to take her to school.The twins won’t see each other until Christmas break & are going to miss each other beyond! Their bond is precious! I am definitely going to be shedding a lot of tears in the next week! ❤️😥❤️

Today is a very emotional day. 💕 I am headed to NYC with Adeline to take her to school.The twins won’t see each other until Christmas break & are going to miss each other beyond! Their bond is precious! I am definitely going to be shedding a lot of tears in the next week! ❤️😥❤️

Shannon Storms Beador

174,279 views • 2 years ago

A new visual reel for a new year! (now with more grit.) Immensely grateful to have played a part in each of these stories. Here’s to what’s next ✨💜 (extra kudos to the amazing Nick Cramer @nervousnick.bsky.social for magically making this reel come together)

A new visual reel for a new year! (now with more grit.) Immensely grateful to have played a part in each of these stories. Here’s to what’s next ✨💜 (extra kudos to the amazing Nick Cramer @nervousnick.bsky.social for magically making this reel come together)

Corey Pettit ✨

10,935 views • 4 months ago