VFX & experiments · Landscape

23 of 3,062 videos

Train Phone Stunt: Previz vs Seedance Final

I created a full short film using free open source AI video models. I jumped into the role of the wizard Trogus and transformed myself into him using AI. Imagine what kind of movies you would have made if you had this tool as a kid!

Mickmumpitz284KX

This time freeze effect is going viral and it's super easy to make using Seedance 2.0 Check the reply for the prompt.

CHRIS FIRST271KX

With this prompt, you can sit courtside for Game 3 as the Knicks look to sweep the 76ers in Philly. Prompts below. Inspired by @johnAGI168

CHRIS FIRST211KX

This entire anime sequence started from ONE Canvas. 👀🔥 I wanted to see how far I could push the new Canvas-first workflow in the upgraded version of Dreamina on a real project. So I built everything inside the same Canvas: → Created my characters → Built detailed Character Sheets → Locked their vis

Pierrick Chevallier | IA88.7KX

You can now turn images into explorable 3D worlds. Locally. For free. The method involves piloting a virtual 360 degree drone through your scene to map out your world and generate a synthetic dataset for gaussian splat training. Here is how it works 👇

Mickmumpitz54.5KX

I love open source AI in @ComfyUI because it lets me control every step. For this spaceship shot I tracked the camera, designed layout geometry in Blender, exported depth maps, prompted the final look with an AI image editor, and jumped into Photoshop to clean it all up.

Mickmumpitz48.1KX

Changing the camera with MiniMax H3 and SAM 3D Body while keeping the environment consistent. If I'd known I'd get it working this fast, I would have said something smart... More examples below!

Mickmumpitz25.4KX

Seedance 2.5 Omni Reference dance transfer workflow

One taxi. Six worlds. Zero visible cuts. 👀 This is the kind of transition challenge I love throwing at AI video. The trick: never transform the taxi. Only change the world outside using buses, wipers, tunnels, trucks and light flares as natural transition masks. Simple rule. Endless possibilities.

Pierrick Chevallier | IA3.9KX

Kling 4.0 Flash paper cigarette cinematic test

LivePortrait + Elevenlabs audiochange. Pretty sweet technique to get some control :D

Antti Karppinen 🎨2.2KX

Workflow experiment. Flux Lora -> Various images in ComfyUI -> Animate in RunwayML -> Make a video with iPhone -> Animate videoclips with Live Portrait to get lipsync and facial expressions :D @runwayml

Antti Karppinen 🎨1.1KX

Example workflow for making your characters move and talk. Midjourney+Luma.ai+Elevenlabs+ComfyUI (liveportrait video2video) Getting better every day, and more control is always better! @midjourney @LumaLabsAI @elevenlabs

Antti Karppinen 🎨878X

Experimenting with good workflow getting wanted characters to talk. Using Flux+Lora, @runwayml , @elevenlabs, LivePortrait etc.

Antti Karppinen 🎨725X

How to create a realistic late-night gym vlog with Seedance 2.5? Full prompt below! #Seedance #AIVideo #AIAnimation #GenerativeAI #AIArtCommunity #DreaminaSeedance25 #DreaminaAI #Seedance25 #Seedance #VLOG #ads @noman23761

Noman | AI Filmmaker602X

Seedance 2.5 keeps sneaking music into my clips that I never asked for and prompted against. easy fix: run it through meta’s SAM Audio, isolate the music and just delete it. you keep the SFX's, drop in your own tracks, and suddenly ev

The secret to this shot wasn't the ziggurat. It was the last 4 seconds. 🎬 "Let the darkness breathe. The sun is gone. Stillness, weight, dread." Most AI video rushes the ending. Give it room and it starts feeling like cinema. Nano Banana Pro + Kling 4.

Naruto vs Kaguya What if your favorite anime was a real movie? 🔥 I built this whole thing in one workspace. No jumping between apps, no cluttered storage. Just frame by frame, shot by shot, all inside PixVerse Canvas. @pixverse_official

Want to make money with AI? 🤑 New AICL modules are dropping over the next few weeks covering AI businesses, avatar brands, UGC, client acquisition, scaling + more. → Join now for early access:

Sebastien Jefferies6Threads

Grok animation prompt 🔥👇

Sebastien Jefferies3Threads

Prompt i2v Video powered by @hailuoai_official on @doiton_g 1) Cinematic, brutal close-quarters combat, hyper-realistic, 8K, high-speed action sequence, rendered in Unreal Engine 5, no slow motion. The shot starts locked on the warrior, who is in a low, coiled evasive stance after narrowly dodgin

video video gagal. Dibuang sayang, credit nya ga ada lagi 😂 T2I @midjourney I2V @hailuoai_official on @doiton_g