Ege

@egeberkina • 75,865 subscribers

Art Director | Creative Ambassador @ElevenLabs & @Adobe | AI Creator

Shorts

Some things just get better with time

Some things just get better with time

899,203 次观看

Recently these super realistic live TV broadcast shots have been going viral everywhere Tried making one myself using GPT Image 2 + Kling 3.0 Prompt: A screenshot from a live Wimbledon TV broadcast during a packed Centre Court match. The camera cuts to the audience, an unbelievably attractive woman in her 20s with long black hair, flawless skin, elegant makeup, and a luxurious aura, seated in the VIP section wearing a sophisticated cream-white low-cut summer outfit with subtle jewelry. She smiles naturally while reacting to the match, unaware she's on camera. Wealthy spectators and champagne glasses around her, old-money tennis atmosphere, shallow depth of field. Full live tennis broadcast overlay: scoreboard, network watermark, broadcast graphics, 16:9 aspect ratio. The image looks exactly like a real TV screenshot, telephoto broadcast lens, realistic live color grading, slight compression artifacts, interlacing grain, subtle motion blur, imperfect live-camera framing.

Recently these super realistic live TV broadcast shots have been going viral everywhere Tried making one myself using GPT Image 2 + Kling 3.0 Prompt: A screenshot from a live Wimbledon TV broadcast during a packed Centre Court match. The camera cuts to the audience, an unbelievably attractive woman in her 20s with long black hair, flawless skin, elegant makeup, and a luxurious aura, seated in the VIP section wearing a sophisticated cream-white low-cut summer outfit with subtle jewelry. She smiles naturally while reacting to the match, unaware she's on camera. Wealthy spectators and champagne glasses around her, old-money tennis atmosphere, shallow depth of field. Full live tennis broadcast overlay: scoreboard, network watermark, broadcast graphics, 16:9 aspect ratio. The image looks exactly like a real TV screenshot, telephoto broadcast lens, realistic live color grading, slight compression artifacts, interlacing grain, subtle motion blur, imperfect live-camera framing.

1,192,275 次观看

15 sec video. Generated in under 15 seconds! H3 Max is an absolute monster.

15 sec video. Generated in under 15 seconds! H3 Max is an absolute monster.

209,577 次观看

This only cost $0.54 and took 18 seconds to generate. Insane quality for the price and speed.

This only cost $0.54 and took 18 seconds to generate. Insane quality for the price and speed.

76,958 次观看

Just tried Seedance 2.0 and with just a few words I was able to create a really solid ad

Just tried Seedance 2.0 and with just a few words I was able to create a really solid ad

314,076 次观看

I asked Seedance 2.0 how the pyramids were built… and the result is kinda terrifying

I asked Seedance 2.0 how the pyramids were built… and the result is kinda terrifying

277,004 次观看

Since Midjourney announced that they support creating videos with specific start and end frames, I had to try it. So I retextured the images with the JSON below and then used start and end frames to create a short video! Prompt 👇

Since Midjourney announced that they support creating videos with specific start and end frames, I had to try it. So I retextured the images with the JSON below and then used start and end frames to create a short video! Prompt 👇

327,595 次观看

Just finished a full loop morph animation using Midjourney, especially now that they just dropped HD Video Mode 👀 JSON Prompt 👇

Just finished a full loop morph animation using Midjourney, especially now that they just dropped HD Video Mode 👀 JSON Prompt 👇

223,688 次观看

What if workouts were generated like this? Built a dumbbell routine as a motion sheet with GPT Image 2 Then turned it into a video with Seedance 2.0 I tested 4 exercises in 15s, it works, but 2–3 exercises would probably give the best output. Motion sheet: Monochrome grayscale technical illustration, biomechanically accurate fitness instruction sheet, clean 3D anatomical character, scientific diagram aesthetic, minimalistic, no artistic exaggeration 2x4 grid layout (8 panels total), perfectly aligned cells, equal spacing, thin black borders, numbered from 1 to 8 Neutral athletic human body (gender-neutral), proportional anatomy, consistent character across all panels Dumbbell workout sequence (key positions only): 1. Dumbbell curl (start position) 2. Dumbbell curl (top contraction) 3. Shoulder press (start at shoulder level) 4. Shoulder press (overhead lockout) 5. Dumbbell lateral raise (arms down) 6. Lateral raise (arms at shoulder height) 7. Dumbbell squat (standing start) 8. Squat (bottom position) Top-left: bold number + exercise name (English) Center: full-body pose (clear joint positions) Bottom-left: short technical explanation (2–3 lines, correct form cues) Overlay: directional arrows showing movement path (up/down/arc) Correct joint alignment, neutral spine, proper elbow and knee positioning, realistic weight distribution, no exaggerated motion Highly detailed grayscale shading, soft studio lighting, subtle shadows, clean linework, medical / sports science diagram quality Pure white background No colors, no background environment, no extra elements, no stylization, no blur

What if workouts were generated like this? Built a dumbbell routine as a motion sheet with GPT Image 2 Then turned it into a video with Seedance 2.0 I tested 4 exercises in 15s, it works, but 2–3 exercises would probably give the best output. Motion sheet: Monochrome grayscale technical illustration, biomechanically accurate fitness instruction sheet, clean 3D anatomical character, scientific diagram aesthetic, minimalistic, no artistic exaggeration 2x4 grid layout (8 panels total), perfectly aligned cells, equal spacing, thin black borders, numbered from 1 to 8 Neutral athletic human body (gender-neutral), proportional anatomy, consistent character across all panels Dumbbell workout sequence (key positions only): 1. Dumbbell curl (start position) 2. Dumbbell curl (top contraction) 3. Shoulder press (start at shoulder level) 4. Shoulder press (overhead lockout) 5. Dumbbell lateral raise (arms down) 6. Lateral raise (arms at shoulder height) 7. Dumbbell squat (standing start) 8. Squat (bottom position) Top-left: bold number + exercise name (English) Center: full-body pose (clear joint positions) Bottom-left: short technical explanation (2–3 lines, correct form cues) Overlay: directional arrows showing movement path (up/down/arc) Correct joint alignment, neutral spine, proper elbow and knee positioning, realistic weight distribution, no exaggerated motion Highly detailed grayscale shading, soft studio lighting, subtle shadows, clean linework, medical / sports science diagram quality Pure white background No colors, no background environment, no extra elements, no stylization, no blur

99,122 次观看

Used GPT-4o to create this UGC style ad concept for the Philips 7000 Series shaver. Before ➝ After No actors. No filters. Just clean, believable storytelling.

Used GPT-4o to create this UGC style ad concept for the Philips 7000 Series shaver. Before ➝ After No actors. No filters. Just clean, believable storytelling.

211,617 次观看

Employee of the month 🍔 Seedance 2.0 Prompt: 100% real-life filmed texture, iPhone documentary look, handheld single take, natural lighting, slight breathing shake, random focus shifts, subtle lens dirt on edges. Environment A busy McDonald's parking lot during lunch hour. Cars pulling in, people walking out with trays, fries smell in the air. Main Character A tired McDonald's employee (Image1) stepping outside for a break holding a tray with a Big Mac and fries. Sudden Event (Hook 0–3s) The ground cracks open. A giant greasy burger monster made of melted cheese, beef patties, and lettuce bursts out of the asphalt, towering over the restaurant. Cars screech. Customers scream. 13-Second One-Take 0–2s Chaos. The burger monster smashes a parked car. 2–3s Camera lands on the employee calmly holding the tray. 3–4s They slowly pick up a single fry. 4–6s Golden particles start glowing around the fry. 6–8s The fry multiplies into hundreds of glowing golden fries spinning around the employee like nanotech. 8–10s They snap their fingers. All fries launch like missiles at the monster. 10–12s The monster explodes into sesame seeds and lettuce. 12–13s Employee shrugs and takes a bite of the Big Mac. McDonald's logo appears.

76,440 次观看

Omni reference in Seedance 2.0 is really a powerful feature

Omni reference in Seedance 2.0 is really a powerful feature

69,849 次观看

Midjourney start and end frames rock 🔥 I retextured the images using GPT-4o and the JSON below to give them a voxel-style makeover, then turned them into smooth animations with Midjourney Video! Prompt 👇

Midjourney start and end frames rock 🔥 I retextured the images using GPT-4o and the JSON below to give them a voxel-style makeover, then turned them into smooth animations with Midjourney Video! Prompt 👇

147,886 次观看

Got early access to MiniMax H3, so I had to try something with it. I generated 5 still frames for a fictional series intro, used them as Omni References and turned them into a short title sequence. Just sharing my first test and there's still a lot more to explore, but it's been fun playing around with it so far. I'll keep experimenting and share more as I go. #MiniMaxH3

Got early access to MiniMax H3, so I had to try something with it. I generated 5 still frames for a fictional series intro, used them as Omni References and turned them into a short title sequence. Just sharing my first test and there's still a lot more to explore, but it's been fun playing around with it so far. I'll keep experimenting and share more as I go. #MiniMaxH3

33,074 次观看

What if yoga routines were generated like this? Built a yoga motion sheet with GPT Image 2, created a character in Midjourney, then uploaded both into Seedance 2.0 to generate the final video where the character follows the motion sheet Tested 3 exercises in 15s, much cleaner flow and better consistency You can upload any character and use this workflow/prompt to generate your own version too Motion sheet prompt: Monochrome grayscale technical illustration, biomechanically accurate yoga instruction sheet, clean 3D anatomical character, scientific diagram aesthetic, minimalistic, no artistic exaggeration 1x3 grid layout (3 panels total), perfectly aligned cells, equal spacing, thin black borders, numbered from 1 to 3 Neutral athletic human body (gender-neutral), proportional anatomy, consistent character across all panels Yoga sequence (key positions only): Forward fold (Uttanasana, hip hinge) Plank pose (full body alignment) Downward facing dog (inverted V, hips lifted) Top-left: bold number + pose name (English) Center: full-body pose (clear joint positions) Bottom-left: short technical explanation (2–3 lines, alignment + breath cues) Overlay: subtle directional arrows showing flow (down → forward → back/up) Correct joint alignment, neutral spine where required, grounded feet, stable shoulders, controlled flexibility, no exaggerated stretching Highly detailed grayscale shading, soft studio lighting, subtle shadows, clean linework, medical / sports science diagram quality Pure white background No colors, no background environment, no extra elements, no stylization, no blur

What if yoga routines were generated like this? Built a yoga motion sheet with GPT Image 2, created a character in Midjourney, then uploaded both into Seedance 2.0 to generate the final video where the character follows the motion sheet Tested 3 exercises in 15s, much cleaner flow and better consistency You can upload any character and use this workflow/prompt to generate your own version too Motion sheet prompt: Monochrome grayscale technical illustration, biomechanically accurate yoga instruction sheet, clean 3D anatomical character, scientific diagram aesthetic, minimalistic, no artistic exaggeration 1x3 grid layout (3 panels total), perfectly aligned cells, equal spacing, thin black borders, numbered from 1 to 3 Neutral athletic human body (gender-neutral), proportional anatomy, consistent character across all panels Yoga sequence (key positions only): Forward fold (Uttanasana, hip hinge) Plank pose (full body alignment) Downward facing dog (inverted V, hips lifted) Top-left: bold number + pose name (English) Center: full-body pose (clear joint positions) Bottom-left: short technical explanation (2–3 lines, alignment + breath cues) Overlay: subtle directional arrows showing flow (down → forward → back/up) Correct joint alignment, neutral spine where required, grounded feet, stable shoulders, controlled flexibility, no exaggerated stretching Highly detailed grayscale shading, soft studio lighting, subtle shadows, clean linework, medical / sports science diagram quality Pure white background No colors, no background environment, no extra elements, no stylization, no blur

61,586 次观看

Dreamina Seedance 2.0 can change what's inside any video with one prompt. Characters, cars and even monsters. Here are a few quick examples 👇

Dreamina Seedance 2.0 can change what's inside any video with one prompt. Characters, cars and even monsters. Here are a few quick examples 👇

59,105 次观看

This feels like a deleted sitcom episode

This feels like a deleted sitcom episode

25,814 次观看

One of my first MiniMax H3 tests Omni Reference worked really well here. I only provided references for the woman, the man and the horse and then used the prompt below 👇 Prompt: Use @ Image1 as the man reference. Use @ Image2 as the woman reference. Use @ Image3 as the horse reference. Create a surreal 15-second fashion-film sequence inside a minimalist monochrome blue studio. The woman performs an elegant contemporary dance. The man casually walks into frame wearing a completely serious expression. Without explanation, he immediately joins the choreography. His movements are awkward, strangely confident, almost ritualistic. The woman never acknowledges him. The horse behaves as though both dancers are part of its routine. It wanders through the studio. Runs behind them. Appears from impossible places. Stops. Looks directly into the camera. Leaves. Returns again. Sometimes all three performers accidentally synchronize for one beat before drifting apart again. The choreography becomes increasingly absurd but remains perfectly cinematic. Every movement is intentional. Every frame feels designed. Throughout the sequence, premium kinetic typography appears as part of the composition, not subtitles, but editorial motion graphics inspired by high-end After Effects title design. Animated words flash for only a few frames: THE GARDENER. THE DRIVER. THE HORSE. THE WOMAN. KNIFE. MOVE. FASTER. AGAIN. THE EXIT. These words slam into frame, wrap around the dancers, disappear behind bodies, stretch with motion blur, rotate in 3D, fragment into pieces, reveal through masks, pulse with the bass, smear across cuts, become oversized, tiny, vertical, upside down, and constantly transform using premium motion-design techniques. Add abstract editorial graphics: animated arrows, circles, blueprint lines, tape labels, interface markers, halftone textures, scribbles, grain, tracking graphics, geometric overlays, chromatic aberration, liquid masks, flash frames, split screens, typography trails, speed ramps and graphic wipes. Music evolves into strange electronic art-pop. Analog synths. Mechanical breathing. Heavy bass. Everything is synchronized to the rhythm. Final close-up. The woman whispers: "Again." The man quietly smiles for the first time. The horse suddenly sprints directly toward the camera. The word AGAIN. fills the screen before an instant cut to black.

One of my first MiniMax H3 tests Omni Reference worked really well here. I only provided references for the woman, the man and the horse and then used the prompt below 👇 Prompt: Use @ Image1 as the man reference. Use @ Image2 as the woman reference. Use @ Image3 as the horse reference. Create a surreal 15-second fashion-film sequence inside a minimalist monochrome blue studio. The woman performs an elegant contemporary dance. The man casually walks into frame wearing a completely serious expression. Without explanation, he immediately joins the choreography. His movements are awkward, strangely confident, almost ritualistic. The woman never acknowledges him. The horse behaves as though both dancers are part of its routine. It wanders through the studio. Runs behind them. Appears from impossible places. Stops. Looks directly into the camera. Leaves. Returns again. Sometimes all three performers accidentally synchronize for one beat before drifting apart again. The choreography becomes increasingly absurd but remains perfectly cinematic. Every movement is intentional. Every frame feels designed. Throughout the sequence, premium kinetic typography appears as part of the composition, not subtitles, but editorial motion graphics inspired by high-end After Effects title design. Animated words flash for only a few frames: THE GARDENER. THE DRIVER. THE HORSE. THE WOMAN. KNIFE. MOVE. FASTER. AGAIN. THE EXIT. These words slam into frame, wrap around the dancers, disappear behind bodies, stretch with motion blur, rotate in 3D, fragment into pieces, reveal through masks, pulse with the bass, smear across cuts, become oversized, tiny, vertical, upside down, and constantly transform using premium motion-design techniques. Add abstract editorial graphics: animated arrows, circles, blueprint lines, tape labels, interface markers, halftone textures, scribbles, grain, tracking graphics, geometric overlays, chromatic aberration, liquid masks, flash frames, split screens, typography trails, speed ramps and graphic wipes. Music evolves into strange electronic art-pop. Analog synths. Mechanical breathing. Heavy bass. Everything is synchronized to the rhythm. Final close-up. The woman whispers: "Again." The man quietly smiles for the first time. The horse suddenly sprints directly toward the camera. The word AGAIN. fills the screen before an instant cut to black.

20,948 次观看

I mean… look at this 👀

I mean… look at this 👀

27,675 次观看

Now I actually wanna play it

Now I actually wanna play it

25,380 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

I think I've burned almost all of my credits testing Dreamina Seedance 2.5 over the past few days. I wanted to push every major feature as far as I could instead of just making another "look what this can do" video. Here's what actually stood out: multi character consistency, timestamp prompting, longer generations and a few other surprisingly useful features. A quick breakdown 👇 Dreamina is ByteDance's AI creation platform (from the same parent company as TikTok), and it's the first place where Dreamina Seedance 2.5 is available globally.

I think I've burned almost all of my credits testing Dreamina Seedance 2.5 over the past few days. I wanted to push every major feature as far as I could instead of just making another "look what this can do" video. Here's what actually stood out: multi character consistency, timestamp prompting, longer generations and a few other surprisingly useful features. A quick breakdown 👇 Dreamina is ByteDance's AI creation platform (from the same parent company as TikTok), and it's the first place where Dreamina Seedance 2.5 is available globally.

299,928 次观看 • 2 个月前

The first iPhone without a camera! This iPhone 17 Pro spec ad goes hard. Nano Banana really solves a lot of video production challenges in different ways. Credit: Simon Meyer & Ciro Kavouras

The first iPhone without a camera! This iPhone 17 Pro spec ad goes hard. Nano Banana really solves a lot of video production challenges in different ways. Credit: Simon Meyer & Ciro Kavouras

329,127 次观看 • 1 年前

Just tested Runway Aleph 2.0 and this blew my mind a bit lol I saw a video like this when Aleph first released and with the new Aleph 2.0 I wanted to create my own version. You basically select a single frame from the video, apply a change to that specific frame using Nano Banana Pro, GPT Image 2 or Gen-4 and based on the newly generated image Aleph propagates the change through the entire shot. It's really cool seeing the whole sequence adapt from just one edited frame

Just tested Runway Aleph 2.0 and this blew my mind a bit lol I saw a video like this when Aleph first released and with the new Aleph 2.0 I wanted to create my own version. You basically select a single frame from the video, apply a change to that specific frame using Nano Banana Pro, GPT Image 2 or Gen-4 and based on the newly generated image Aleph propagates the change through the entire shot. It's really cool seeing the whole sequence adapt from just one edited frame

88,610 次观看 • 4 个月前

Still hiring fitness models for your videos? Let me show you how I made this entire fitness scene with Midjourney!

Still hiring fitness models for your videos? Let me show you how I made this entire fitness scene with Midjourney!

198,889 次观看 • 1 年前

Just having some fun with The Odyssey + Grok Imagine Can’t wait to see what everyone creates. Good luck guys!

Just having some fun with The Odyssey + Grok Imagine Can’t wait to see what everyone creates. Good luck guys!

14,708 次观看 • 1 个月前

AI video is moving beyond prompts and Flova’s all-in-one, agent native workflow makes that shift feel real. I wasn’t expecting the Agent to handle this much of the production. I used Seedance 2.5 inside Flova to create this fragrance commercial and the workflow turned out to be just as impressive as the final result. Here’s a step by step breakdown of the entire process 👇

AI video is moving beyond prompts and Flova’s all-in-one, agent native workflow makes that shift feel real. I wasn’t expecting the Agent to handle this much of the production. I used Seedance 2.5 inside Flova to create this fragrance commercial and the workflow turned out to be just as impressive as the final result. Here’s a step by step breakdown of the entire process 👇

11,935 次观看 • 1 个月前

Killer work… these are SO realistic 🤯 Simon Meyer just dropped one of the cleanest ultra-realistic workflows I’ve ever seen! He generated the images on Freepik (ByteDance Seadream), upscaled skin on Enhancor and animated them with ByteDance Seadance. Total cost? ~€80 for animation credits + €30 for Freepik sub

Killer work… these are SO realistic 🤯 Simon Meyer just dropped one of the cleanest ultra-realistic workflows I’ve ever seen! He generated the images on Freepik (ByteDance Seadream), upscaled skin on Enhancor and animated them with ByteDance Seadance. Total cost? ~€80 for animation credits + €30 for Freepik sub

55,917 次观看 • 1 年前

How to get consistent characters + solid lipsync One of my fave artists, Simon Meyer, tested pretty much every tool out there such as Hedra, HeyGen, Dreamina, Higgsfield but landed on this workflow: Characters → Seadream in Freepik (Prompt 👇) Video → Seadance (20+ gens per shot) Music → Suno Lipsync → Sync. I’ve been following Simon’s work and this method looks awesome! Huge appreciation to Simon for sharing his process!

How to get consistent characters + solid lipsync One of my fave artists, Simon Meyer, tested pretty much every tool out there such as Hedra, HeyGen, Dreamina, Higgsfield but landed on this workflow: Characters → Seadream in Freepik (Prompt 👇) Video → Seadance (20+ gens per shot) Music → Suno Lipsync → Sync. I’ve been following Simon’s work and this method looks awesome! Huge appreciation to Simon for sharing his process!

37,082 次观看 • 1 年前

没有更多内容可加载