This is "Eve & Adam" Tips below on how I made this using Gemini, JSON prompts (and why), Runway Aleph, and Veo3. Spoilers below. Watch before reading 🤘

Eve and Adam is a story about a brother and sister who are part human, part machine—the first of what could be the next evolution of the human species. It all started with an idea of someone shooting at the moon. I asked myself, why would anyone do that? Each answer led to another question, and the story of "Eve and Adam" began to unfold. I wanted to capture the nostalgia of films like Close Encounters of the Third Kind and Escape to Witch Mountain, so I used Gemini to research the equipment those films were shot on and to help craft prompts that would maintain that classic look. I used Veo3 text-to-video and image-to-video for the visuals.

This project marked my first experience with JSON prompting. While I skipped the social media debate about whether JSON prompting gives better results —after three years of crafting natural language prompts in paragraph form, the structure this format provided simply made sense to my brain. First, I described the shot I wanted to create to Gemini, which then gave me a prompt in JSON format that I would feed into Veo3. I'd run an initial generation without even reading the prompt, just to see the output. Once I saw how far off the initial generation was from my vision, I'd then read the prompt and find the exact category I needed to tweak—be it lighting, composition, or the subject itself—thanks to the prompt's structured format. To me, this was far easier than revising a block of natural language text. Another advantage: I could copy and paste the entire JSON prompt into Veo3 due to its large token limit, whereas other platforms would hit their character count maximum. Example prompt: { "shot_name": "Aerial Shot (AS) - Car on Dirt Road into Forest", "camera": { "type": "Wide Shot", "movement": "Aerial shot, car turns right off highway onto dirt road, following the car then craning up at the moon in the sky above the forest trees", "lens": "Panavision lenses", "focus": "Car and forest in focus, then car fading", "lighting_direction": "Backlit by evening sky" }, "setting": { "environment": "Highway and a Narrow dirt road leading into dense, overgrown Pacific Northwest forest", "time_of_day": "Night", "atmosphere": "Shifting from isolated to mysterious and ominous" }, "subject": { "main_subject": "Late 1970s muscle car", "details": "Kicking up significant dust, becoming a tiny, fading speck, tail lights receding" }, "visual_style": { "genre": "Action/Sci-Fi Drama", "film_stock": "Kodak 35mm film (Eastman 100T 5247)", "color_grade": "Gritty, natural with deepening purple shadows, cinematic", "rating_tone": "PG-13", "overall_feel": "Cinematic masterpiece" }, "composition": { "elements": "Car swallowed by immense, looming trees; road disappearing into wilderness" }, "implied_elements": { "sound": "Crunch of tires on dirt, rustling leaves, growing silence" } } ]

I did this shot by shot, in a linear fashion. I added clips to my timeline in Premiere until the entire story was roughly laid out. On this first pass, the quality of the shots wasn't the priority; I just needed placeholders to begin understanding the film's flow, pacing, and tone. Then I went back to the start of the timeline and regenerated and refined each shot. I did this hundreds of times. I used Runway Aleph to fix inconsistencies in certain shots, as well as change lighting from day to night featuring the same characters. It came out right as I was nearing the end of making this, so I definitely need to spend more time with it, but this kind of natural language in-painting is amazing. Veo3 provides an 8-second clip with sound effects, dialogue, and sometimes even baked-in music. For better sound design and mixing control, we need to export individual stems, so I used Lalal to split the audio. Veo3’s audio often reflects the scene’s tone—for example, tense scenes get tense music—but it cuts off abruptly at the 8-second mark. One trick I used was to upload the 8 second clip’s audio to Suno and use it as inspiration for a longer sound design or music track. This gave me better better audio consistency when cutting between shots in a particular scene. The main theme music is an original song I wrote years ago when I was in a band. I uploaded the recording to Suno and created variations in different styles that serve as Adam's theme song. I love how this tech isn't just helping me visualize new ideas; it's also breathing new life into old ones. I don't think of this as a finished short film, but instead as a starting point. I can pitch this concept to a studio as a TV series or a feature and show this as a teaser. If it gets picked up, we can shoot it for real. This is exactly why this technology needs to be taught in film schools today. Students can pre-visualize their scripts with AI, see what’s working and what isn’t, then shoot it with real actors on set for intimate scenes, while leveraging AI for any big-budget special effects shots. If you're currently in film school and these tools aren't being taught, I have two words for you: Curious Refuge. One question I know I'll be asked is, "How long did this take to make?" The misleading answer is three weeks. But the real answer, as anyone who has worked in production knows, is years. Years of film school and working as an editor on traditional productions cannot be discounted or ignored, because while generative AI excels at creating visuals, it's currently terrible at storytelling. It's not great at writing scripts and definitely can't edit well yet, so those aspects were done traditionally using the skills I learned from a career in post-production. The good news is you don't have to spend years learning every aspect. There are plenty of knowledgeable people in this space looking to connect and collaborate. Team up. Lastly, I don't believe AI cinema will replace traditional cinema; instead, they will co-exist as separate mediums or merge as an evolution of VFX. We’re still going to need actors, writers, editors, and VFX artists, likely even more than before, given the increased demand for productions that these tools will facilitate. Whether it's AI, CGI, live-action film, or theater, at its core, it's all just storytelling. But to me, having this level of visual effects available and affordable is a dream come true. So, experiment, ask questions, and most importantly, have fun! ✌️

Tools used: Gemini, Veo3, Freepik, Runway, Magnific, Midjourney, ElevenLabs, Suno, Kling, Hailuo, Dreamina, Luma, Topaz

Link to 4K video on Youtube:

I know it’s not “complete” but it is One the best I’ve seen in this space. 7 minutes or so I didn’t stop to check on something else. An insta retweet deserved right here.

Much appreciated 🙏 so good to hear thank u!

Masterful brother. Shared! Hopefully this gets millions of hits.

Always appreciate you bro! 🫶

This is great - really high quality. More compelling than many TV productions I've seen. Character consistency is definitely good enough to tell the story.

Appreciate it, thanks!

This is such quality work. The care and detail that you’ve put into it shines through. I was gripped to the very end. It’s so well done in every aspect. Thanks for the detailed insights into your workflow. I learned a lot reading the entire thread.

Thank you for saying so and for taking the time to read the posts and watch the entire thing. Much appreciated brother! 🤘

Pleasure. It was so easy to watch the whole thing because it was so good! I loved it. You’re operating at a higher level.

Thanks for sharing. I would trim a couple lines and leave a bit more suspense with the eve reveal.

Like the black and white treatment. Always room to trim!

Great story! I love the acting, you really know how to make a character interesting. Tbh, I was a bit sad when the video ended. I hope we’ll see the next part soon!

Thanks Halim, much appreciated! Who knows maybe I’ll pitch this to Promise and see what happens!

I think I breathed about 3 times during the whole film. Great work, at times I forgot it was Ai the story drew me in.

So awesome to hear thank u! Keep breathing 😁

@imagineFERA This is really great man. Appreciate the run down of process and example JSON. I actually did a comparison recently between natural language prompts vs JSON so it was cool to see it being used to good effect and the rationale behind it too.

@imagineFERA Thanks Marco! I’m all for people using whatever works for them. For me the structured breakdown of the prompt just made sense and allowed me to quickly find and tweak what I needed!

@imagineFERA you mention you used Aleph to relight - how did you work around the 8s Veo3 output vs the 5s allowed in Aleph? split it in 2?

@imagineFERA Yeah I already had the piece cut in Premiere so there weren’t any clips longer than 5 seconds at that point. The I just exported the clip I needed into Aleph and made the fix. Saved the inpainting for the end!

@imagineFERA Sick! How did you find output quality? Did you just do a final update in topaz?

@imagineFERA Dude… i put each clip through Astra, clip by clip. It was mind numbing. Then I unpressed the whole finished video in Topaz. We needed 1080p raw outputs yesterday 😂

@imagineFERA Wow

Yooo this 🔥 🔥

🙌

You sir, are a beast! 👏👏👏 Send me the YT so I can feature it next week.

Here you go sir. Appreciate it! Eve and Adam - AI Cinema

@MetaPuppet #AIFilmmaking Singularity achieved right here. Spectacular! John Carpenter take note. 👏🔥

@plattcreative 😂 That's high praise. Thank you!

Also really good sound design

Sound design is so overlooked in AI film!

This is as good as it can be right now. I didn't skipped a second. In one year we will have full movies that are great to watch. Really-really great job!

Appreciate it! Yes eventually the stories will be louder than the tools used to tell it. Working on it!

By far the best example of story, character, pacing and artistry with generative AI. Bravo.

Much appreciated!

@MetaPuppet amazing bro!! Would love to see you explain these two things briefly… what’s the workflow?and how did you achieve character consistency? Did you used txt—>vid or img—> vid

Thank you! A lot of failed gens. But once I had the character I liked using t2v, I saved the frame as an asset in Flow and then would prompt for that character to be in whatever different setting I needed and veo did a decent job of switching the setting but keeping the character.

Got it! thanks. Bro this is one of the brilliant stories told using AI! keep going! would love a detailed breakdown in your coming posts!!

This is probably the most amazing use of AI for filmmaking I’ve seen. Game changer

Appreciate it!

Would love to learn more from you. Great content and storytelling.

This is by far the best movie I have seen with AI.😳🙌 The story telling and character consistency is next level. Thank you for taking this to a level above a raccoon riding a surfboard.

😂 Appreciate it!

underrated part of this short is the dialogue, it's superb. Loved the FBI interactions with the locals, felt really natural!

Appreciate you saying so, thanks!

How did you keep character consistency?

I used runway references for some shots and also image to video in Flow and prompt for the same character in a different setting, veo3 can pull it off

Wow.

Robert! Thanks ✌️

Incredible. And thanks for the detailed write up!!

Thank you for reading it!

@LudovicCreator Impressive, so good

@LudovicCreator Thanks!

This is the first AI movie I saw that is coherent and looks mostly "not-AI". One feedback: it's way too dark. I had to go to completely dark room to enjoy it. In well lit room I couldn't see half of what was happening 😁

Thanks! I should have it color corrected by a professional!

granny wilding😂

😂

How does this only have 373 likes? Amazing work.

Thank u!

I just watched the future

🙌

Wonderful work 👏

Thank you Umesh!

Stunning and creative. One can see your history of experience and really great to share the making of story. It’s going to inspire and empower a lot of creative minds

Thank u!

Ahmazing work.. wow!!!! I'm curious about how much you think this cost to produce.. especially having used Veo3, which is so expensive.

Appreciate it! Hard to calculate as I didn't keep track of the gens, but Imagine the cost of doing this as a traditional production 😳

Ohh.. I totally get that, the cost is a tiny fraction of what it would be with a traditional production. You really did SUCH a great job w/ this.. I'm inspired!

Please tell us you’re already working on the next 90 minutes!!!

Need a little sun first 😂

Man, this is by far the best thing I've watched yet, you've been cooking!!! Totally agree about the process & your insights about it, this is the way! Congrats mate, it's extremely good!!! 🖤🖤🖤

Yo! Thank you Silva! Much appreciated sir!

really impressive how you structured everything, especially the linear approach with placeholders. makes total sense for pacing. excited to see more from you!

Thanks man appreciate it!

WoW this is Wild! All the shots are great and it's the first time i see such consistent caracters! I guess u used image to video in veo 3 for having this consistency, but the first image? Did It came from midjourney? Did u use omniref to keep the caracters or maybe references in Runway? Thanks for explaining the process, It helps a lot!

This is incredible, well done!

@DeeterGaming Thank u!