Jerrod Lew

@jerrod_lew • 19,555 subscribers

Artist, creator and educator. Teaching you to tell stories without limits.

Shorts

840,303 views

372,650 views

151,480 views

71,210 views

69,187 views

33,262 views

26,779 views

59,384 views

33,241 views

30,075 views

19,063 views

38,706 views

12,507 views

13,874 views

13,774 views

23,778 views

38,037 views

Videos

sweetdream.ai

Watch Anya Live

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

Private Show

Join now for exclusive access

Free preview available • Premium content

1,732,549 views • 1 year ago

35,665 views • 19 days ago

321,345 views • 10 months ago

92,240 views • 2 months ago

43,024 views • 1 month ago

92,007 views • 4 months ago

323,466 views • 1 year ago

196,207 views • 1 year ago

70,147 views • 4 months ago

44,231 views • 2 months ago

230,909 views • 1 year ago

56,247 views • 5 months ago

20,587 views • 1 month ago

110,675 views • 1 year ago

79,897 views • 10 months ago

87,295 views • 1 year ago

45,434 views • 5 months ago

33,687 views • 4 months ago

35,672 views • 5 months ago

Live Cam

Jerrod Lew

Shorts

Used Claude Design and Opus 4.7 to design a personal dashboard. With Personal AI becoming more accessible in 2026, I always envisaged that one day we could have our own personal OS as well. Here's what I came up with!

Google Nano Banana works with annotations. Create an image and add characters, objects and text prompt annotations. Use this as a reference and ask Nano Banana to follow the instructions. It managed to place everything perfectly into the shot.

Connect Claude to Blender to create and edit 3D models. I haven't used Blender in ages, but have fond memories doing the famous donut tutorial. I gave Claude an image of a donut, and it got to work immediately to match colors, sprinkles, frosting and even the lights! So cool!

Combining ChatGPT Images 2.0 and Seedance 2.0 together. Character sheets are just perfect for using as a reference for your videos. Can really help with consistency. From this character sheet here, I am able to reimagine the same character in different situations. 1. Runner

Here's how you can isolate individual images from this ChatGPT Image 2.0 prompt. 1. Ask ChatGPT to label each individual frame with a number. 2. Then with the new image, ask again to isolate the specific scene. Video tutorial:

Awesome prompt from Amira! After creating this image, ask Nano Banana 2 to create new angles + upclose shots. Then use them all as a reference for Omni Flash to create 10 second adverts. Example here:

Use Gemini Omni Flash create graphics and fast-paced edits. I uploaded a photo of a car, and prompted Omni Flash to create a spec ad! Here's the result, prompt in the comments!

Google Nano Banana Pro can continue the story from a single image. Create your first frame and then keep iterating by prompting to show what happens next. Here's a quick example using Freepik Spaces.

ChatGPT 5.5 built a landing page for a product. Created the product brief document, logo and product look with ChatGPT Images 2.0. Animated the product video with Seedance 2.0. Gave everything to Codex to create a landing page.

You can make a character sheet for anything, then bring it to Seedance 2.0. Here is...THE Chicken.

Using Runway Aleph 2.0 to transport us to the past. I visited the Roman Baths in Bath, UK this week and used some footage to be reimagined. Tested Nano Banana 2 and ChatGPT Images 2.0 to get the best shot, and Runway Aleph 2.0 generated everything else.

Seedream 4 can place text in your images. The text can even behind an object. Here's a quick example of the potential!

Outstanding realism with Seedance 2.0 at 4K. Image-to-video with Midjourney 8.2, and a much more detailed prompt.

More character sheet fun with ChatGPT Images 2.0 and Seedance 2.0! This time a drummer, and I was so impressed with how Seedance handled the music, drumming and sounds. Hope you've had a good weekend everyone!

Seedance 1.0 multi-shot is so powerful. It's one of the strongest AI video models I've found that can give you different angles from a single image. It's great for consistency and am hoping this becomes a normalized feature across more tools. Some examples.

Camera prompt tips for Runway GEN-3! Try using these keywords to adjust how the camera moves in your AI Video creations. Do you have any particular favorites?

Videos

Watch Anya Live

Google Veo 3 can create singing and music videos from a single prompt. It's just insane how coherent it is to the video. 🔈Sound On!

Elevenlabs v4 and Seedance 2.5 is an amazing combo. The latest voice model from Elevenlabs is outstanding, I've not had so much control over vocal delivery, tone and emotion before. Combining this with the strongest AI video model is spectacular. Check this out:

I'm a huge Pokémon fan. The dream has always been a high-quality, immersive and story driven game in a procedural open world. On the range of monster-catching games out there, the Pokémon lore is so deep and would love to see this in reality. Tried to bring this life:

FLUX 3 made a 20 second cooking tutorial. Lots of multishot in the footage here! It really loves putting butter everywhere 😂.

GPT-6 Astra generated this shoe advert. Using GPT Images 2.0 it was able to generate the initial shoe product, then bring it to life with storyboards and UGC. Highly recommend connecting a creative MCP like Magnific to ChatGPT! Check out all the images below.

Created a 3D game with Claude Fable 5! All visuals, gameplay and coding done by Claude, I gave it the direction and it took the initiative. Check this out:

Google Gemini 2.0 Realtime just helped me edit a video in Adobe Premiere Pro. Using the live screen feature it was able to see what I was doing and guide me within seconds for how to add a basic blur effect. This is a game changer. Absolutely incredble.

Google Flow and Google Veo 3 works with diagrams. Create a still image and annotate it with arrows and text to prompt movement. Google Flow then does the rest for you, here's some examples.

Google Flow is now powered by Gemini Omni. Upload your videos and edit them within the platform with the new Agent feature. It keeps the movement, audio and character intact whilst making edits in your scene. Here's a quick tutorial:

FLUX 3 is here. Been testing it today, and it is outstanding. 20 second generations, does very well with detailed prompts and with amazing cinematography. Here's some examples:

Google Veo 2 is fantastic when it comes to physics. I put it to the test with a range of outputs to see how liquids and solids would react with each other. What do you think?

Sitting courtside goes wrong! Fantastic prompt from CHRIS FIRST. Had so much fun with this haha.

Google Pics is here. Upload your own videos or connect to Google Photos and make edits with Nano Banana. Google Pics breaks your image into specific layers so you can adjust individually all in one place. Here's a quick look:

Google Veo 3 understands spatial prompts. Upload an image with some annotations and ask Veo 3 to follow the instructions in your prompt. Here's how to do it, and some examples.

Did you ever play Mirror's Edge? A first person perspective gave focusing on parkour and hand-to-hand combat. With Kling 2.6, you can bring that style to your AI videos. Some examples with a demo prompt included!

Suno Studio is absolutely incredible. AI Digital Audio Workstation (DAWs) are here, and we are going to create some incredible music with this. I love how you can generate each instrument with a text prompt. You can even record your own instruments too!

ChatGPT 5.5 has arrived. I created a quick video game with it on Codex. Create an image on ChatGPT Images 2.0, and asked Codex to make a basic funtioning video game referencing it. This took only a few minutes for it to create!

Claude Fable 5 built a 3D product website with Claude Code Generate an image of a product with the Magnific MCP, and convert it into a 3D model. Download that model and give it to Fable 5 to develop an interactive page with. Here's the final result + prompts:

Runway Agent has been launched. Up to 30 seconds long, at 1080p, the agent generates the video outline with your characters and environments first. You can confirm or make any changes before generating. Here's how it looks.