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.

Only one Adobe Firefly video prompt from our research hit production-ready on the first generation. Prompt in comments 👀 It looks you have to direct the camera as much as the model to get the most out of Firefly. Every other video session in our research needed a revision.... show more

ben @ CVPR

14,463 subscribers

12,847 views • 4 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Camera control is no longer in the prompt Meet 3D Motion Control → Set the camera path in 3D → Your scene becomes the video reference the model follows → Same move, every take, exactly where you set it Available now in Magnific

Camera control is no longer in the prompt Meet 3D Motion Control → Set the camera path in 3D → Your scene becomes the video reference the model follows → Same move, every take, exactly where you set it Available now in Magnific

Magnific

610,355 views • 2 months ago

Here are some really tactical ways to optimize the First and last frame capability: — Make sure your prompt includes precise camera motion descriptions for smooth and creative transitions between the first and last frames. — Or, you can simply include the word “transform” in your prompt for a smooth transition — Starting with a closeup in your first frame and then zooming out to a wide-shot in the final frame is an effective way to create a dramatic reveal.

Here are some really tactical ways to optimize the First and last frame capability: — Make sure your prompt includes precise camera motion descriptions for smooth and creative transitions between the first and last frames. — Or, you can simply include the word “transform” in your prompt for a smooth transition — Starting with a closeup in your first frame and then zooming out to a wide-shot in the final frame is an effective way to create a dramatic reveal.

Google AI

28,595 views • 11 months ago

Pause the world. Keep the camera rolling. That was the prompt. Coffee suspended mid-air. People frozen mid-motion. The camera moves through it all like time simply stopped. MiniMax H3 Max generated the full 15s shot in just 35 seconds on Pollo AI. Getting the effect right comes down to how you describe motion, stillness, and camera movement in the same prompt. So we broke ours down line by line. Full prompt + workflow ↓

Pause the world. Keep the camera rolling. That was the prompt. Coffee suspended mid-air. People frozen mid-motion. The camera moves through it all like time simply stopped. MiniMax H3 Max generated the full 15s shot in just 35 seconds on Pollo AI. Getting the effect right comes down to how you describe motion, stillness, and camera movement in the same prompt. So we broke ours down line by line. Full prompt + workflow ↓

Pollo AI

11,206 views • 1 month ago

Every time a new model drops, someone says designers are dead. Fable 5 is the biggest one yet. So I gave it the LottieFiles Creator MCP and asked it to animate. Real Lottie, one prompt, runs in production. Does this kill motion designers, or finally put it in everyone's hands?

Every time a new model drops, someone says designers are dead. Fable 5 is the biggest one yet. So I gave it the LottieFiles Creator MCP and asked it to animate. Real Lottie, one prompt, runs in production. Does this kill motion designers, or finally put it in everyone's hands?

Nattu

36,172 views • 3 months ago

AI video generation has come a long way. 🤯 You can now turn a simple prompt into a complete video — from scenes and characters to motion, camera angles, lighting, and visual effects. No complex editing. No hours of manual work. Just describe what you want, and AI can bring it to life. Want the exact prompt used to create videos like this? Comment “PROMPT” and I’ll share the free prompt link.

AI video generation has come a long way. 🤯 You can now turn a simple prompt into a complete video — from scenes and characters to motion, camera angles, lighting, and visual effects. No complex editing. No hours of manual work. Just describe what you want, and AI can bring it to life. Want the exact prompt used to create videos like this? Comment “PROMPT” and I’ll share the free prompt link.

Future Logic

11,131 views • 21 days ago

Stitching a UFO video into a panorama makes it easier to see the overall apparent motion of the object (a black dot, starting in the lower right). But it also magnifies the parallax illusion, as the static background makes the camera motion less apparent.

Stitching a UFO video into a panorama makes it easier to see the overall apparent motion of the object (a black dot, starting in the lower right). But it also magnifies the parallax illusion, as the static background makes the camera motion less apparent.

Mick West

18,059 views • 4 months ago

One of the biggest challenges in video to motion is scale! Most of the time people think of it as distance to the camera, but when you add multiple people the scale between them almost matters more! At cartwheel - with our newest model - we're really proud to capture distance and character scale accurately

One of the biggest challenges in video to motion is scale! Most of the time people think of it as distance to the camera, but when you add multiple people the scale between them almost matters more! At cartwheel - with our newest model - we're really proud to capture distance and character scale accurately

Andrew Carr 🤸

24,484 views • 4 months ago

Kling 2.6 Motion Capture is so good. It's a huge leap forward. We've been able to do motion capture with AI for a while, but the quality bump finally made this approach useful. Here are the steps: - Get a reference video - record it or get a stock video - Grab the start frame of that video - Edit it using Nano Banana Pro. Ask to replace character and background. - Select the Kling 2.6 Motion Capture model in the video generator on Freepik (now Magnific) - Upload reference video + set the edited start frame - Video prompt can be simple e.g. "Gandalf dancing"

Kling 2.6 Motion Capture is so good. It's a huge leap forward. We've been able to do motion capture with AI for a while, but the quality bump finally made this approach useful. Here are the steps: - Get a reference video - record it or get a stock video - Grab the start frame of that video - Edit it using Nano Banana Pro. Ask to replace character and background. - Select the Kling 2.6 Motion Capture model in the video generator on Freepik (now Magnific) - Upload reference video + set the edited start frame - Video prompt can be simple e.g. "Gandalf dancing"

Martin LeBlanc

35,274 views • 9 months ago

Grok Imagine created an adorable little kitten. To make the video longer, I used the last frame of the first video and re-ran a custom prompt with it 😉

Grok Imagine created an adorable little kitten. To make the video longer, I used the last frame of the first video and re-ran a custom prompt with it 😉

Déborah

805,275 views • 1 year ago

i just generated this AI UGC creative for a teeth whitening product in 10 minutes in Higgsfield (you can now generate in 1080p)... here's my workflow: > deploy a research agent to find UGC style videos that promote products like the one you wanna make a creative for > use gemini 2.5 flash to analyze the creative & get a detailed analysis of each scene (get it to add a placeholder for each image reference in your prompt) > use GPT-image 2 in Higgsfield to extract a frame from each cut-scene & use it as a reference for your generation in the prompt wherever there's a placeholder > send the prompt + all the references to Higgsfields video generator & select Seedance 2.5, then generate it > once you have a finished product, take it to a video editor & add captions / cuts / zooms / music

i just generated this AI UGC creative for a teeth whitening product in 10 minutes in Higgsfield (you can now generate in 1080p)... here's my workflow: > deploy a research agent to find UGC style videos that promote products like the one you wanna make a creative for > use gemini 2.5 flash to analyze the creative & get a detailed analysis of each scene (get it to add a placeholder for each image reference in your prompt) > use GPT-image 2 in Higgsfield to extract a frame from each cut-scene & use it as a reference for your generation in the prompt wherever there's a placeholder > send the prompt + all the references to Higgsfields video generator & select Seedance 2.5, then generate it > once you have a finished product, take it to a video editor & add captions / cuts / zooms / music

EP

28,949 views • 1 month ago

Adobe just launched the beta of Firefly, their AI image creator. And it's incredible! - text-to-image - AI 3D modelling - AI Video editing This is the first AI image generator built towards solving creator problems. Here's a breakdown.

Adobe just launched the beta of Firefly, their AI image creator. And it's incredible! - text-to-image - AI 3D modelling - AI Video editing This is the first AI image generator built towards solving creator problems. Here's a breakdown.

Sudharshan

1,224,268 views • 3 years ago

Okay, motion designers are 100% cooked. Saw on x that Opus 5.5 could do advanced animations and I was skeptical at first. So I gave it a one sentence prompt, and it one shot this in 15 minutes. Will add the prompt below, but this is genuinely mind blowing. This level of work would have costed $8,000 - $10,000 with a motion design team and 3-4 week turnaround with multiple revisions. Claude did it in one go with this prompt: "make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a résumé. go all out." The only thing remaining for humans is creativity and critical thinking.

Okay, motion designers are 100% cooked. Saw on x that Opus 5.5 could do advanced animations and I was skeptical at first. So I gave it a one sentence prompt, and it one shot this in 15 minutes. Will add the prompt below, but this is genuinely mind blowing. This level of work would have costed $8,000 - $10,000 with a motion design team and 3-4 week turnaround with multiple revisions. Claude did it in one go with this prompt: "make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a résumé. go all out." The only thing remaining for humans is creativity and critical thinking.

Leon Abboud

122,923 views • 11 days ago

Made with Seedance 2.5 🎬 This is what happens when cinematic storytelling meets precise AI video control. A packed Friday night. A sudden collision. A cocktail suspended in mid-air. And one bartender moving through frozen time to rebuild the drink before anyone even realizes what happened. 🍸 The attention to liquid physics, ice, garnish movement, character consistency, camera motion, and time transitions is what makes this generation stand out. Prompt below 👇 [Paste the full prompt in the first reply/thread] #AI #Seedance #AIVideo

Made with Seedance 2.5 🎬 This is what happens when cinematic storytelling meets precise AI video control. A packed Friday night. A sudden collision. A cocktail suspended in mid-air. And one bartender moving through frozen time to rebuild the drink before anyone even realizes what happened. 🍸 The attention to liquid physics, ice, garnish movement, character consistency, camera motion, and time transitions is what makes this generation stand out. Prompt below 👇 [Paste the full prompt in the first reply/thread] #AI #Seedance #AIVideo

Sajid AI

72,535 views • 1 month ago

Prompt Studio: Speed in Kling AI 2.6, image to video, with native audio The camera drops straight down the side of a massive megastructure at terrifying speed. Building details stretch into vertical streaks, wind buffets the frame, sudden braking pulses. Extreme vertical motion blur.

Prompt Studio: Speed in Kling AI 2.6, image to video, with native audio The camera drops straight down the side of a massive megastructure at terrifying speed. Building details stretch into vertical streaks, wind buffets the frame, sudden braking pulses. Extreme vertical motion blur.

Alexandra Aisling

29,237 views • 8 months ago

Seedance 2.0 Prompt Share Today's camera technique: Motivated Continuous Camera Move A filmmaking technique frequently used by directors like Steven Spielberg, where the camera moves continuously and every shift in direction is motivated by action within the scene. Instead of cutting between shots, the camera naturally redirects its focus as new subjects enter the frame. You can find the prompt below 👇 Seedance 2.0 on @MartiniArt_

Seedance 2.0 Prompt Share Today's camera technique: Motivated Continuous Camera Move A filmmaking technique frequently used by directors like Steven Spielberg, where the camera moves continuously and every shift in direction is motivated by action within the scene. Instead of cutting between shots, the camera naturally redirects its focus as new subjects enter the frame. You can find the prompt below 👇 Seedance 2.0 on @MartiniArt_

Kōda

157,884 views • 6 months ago

> he turned himself into Tom Holland's Spider-Man > and it reads as real because of one prompt line 1. higgsfield → create image (nano banana pro) 2. upload your normal photo 3. the prompt does the work: > "ultra-realistic, no smoothing, no CGI look" > "looks like real behind-the-scenes footage" 4. that image → kling motion control 5. your video left, the face right → generate 6. the character copies your every move > everyone chases the model > the realism lives in the prompt

> he turned himself into Tom Holland's Spider-Man > and it reads as real because of one prompt line 1. higgsfield → create image (nano banana pro) 2. upload your normal photo 3. the prompt does the work: > "ultra-realistic, no smoothing, no CGI look" > "looks like real behind-the-scenes footage" 4. that image → kling motion control 5. your video left, the face right → generate 6. the character copies your every move > everyone chases the model > the realism lives in the prompt

RetroChainer

43,451 views • 4 months ago

GPT Image 2 + Seedance 2.0 on mitte.ai When using storyboards, I try not to describe every shot in the video prompt as much as possible. To support that, I started adding more details into the storyboards instead. The idea is letting the storyboard carry shot order, pacing, camera logic and continuity while keeping the video prompt simpler. Still experimenting with it but results feel promising. You can check the prompts and result.

GPT Image 2 + Seedance 2.0 on mitte.ai When using storyboards, I try not to describe every shot in the video prompt as much as possible. To support that, I started adding more details into the storyboards instead. The idea is letting the storyboard carry shot order, pacing, camera logic and continuity while keeping the video prompt simpler. Still experimenting with it but results feel promising. You can check the prompts and result.

Kōda

20,687 views • 4 months ago

Video Model Comparison: Image2Video Same input image + text prompt on each model: • Pika 2.0 • OpenAI Sora • Runway Gen-3 • Kling AI 1.6 • Luma Dream Machine • Hailuo MiniMax I used the same prompt that I used to generate this image in Midjourney and chose the best results for each model tested. The prompt didn't include specific camera motion, so it was interesting to see each model's interpretation:

Video Model Comparison: Image2Video Same input image + text prompt on each model: • Pika 2.0 • OpenAI Sora • Runway Gen-3 • Kling AI 1.6 • Luma Dream Machine • Hailuo MiniMax I used the same prompt that I used to generate this image in Midjourney and chose the best results for each model tested. The prompt didn't include specific camera motion, so it was interesting to see each model's interpretation:

Heather Cooper

63,079 views • 1 year ago