Lewpen

Artificial Music: Music Tool: Music Videos:

[Lewpen @Lewpen]

"The Garden" .. Realtime SDF fractal made with JavaScript & WebGL .. #genartclub #generative #gamedev

[Cristóbal Valenzuela @c_valenzuelab]

Transitioning from using a single video model to generate a clip to achieving a finished video is like the transition from coding models that merely autocomplete to coding models that write working software. That moment is finally possible for video.

You describe what you want, and you get what you need. There's something incredibly powerful about simply describing an idea and watching it come to life.

Something we've been working on for years is finally here. I'm incredibly excited to release the most powerful creative agent ever built.

[Rahul @sairahul1]

Holy sh*t, developers are going to lose their minds over this.

Someone just open sourced a repo that gives you 800M free tokens a month across every major LLM.

GPT-4. Claude. Gemini. Llama. Mistral. All of them. Free. Right now.

It's called freellmapi and here's why it changes everything:

→ 800 million free tokens a month — no credit card, no API key
→ Every major model in one place — GPT-4, Claude 3, Gemini Ultra, Llama 3, Mistral
→ Open source, MIT license, drop-in replacement for paid API calls
→ Works with any existing codebase — swap your endpoint, keep your code
→ No usage dashboard, no overage warnings, no surprise billing

Most indie developers spend more on API costs than they earn from their product.

This repo just made that problem disappear.

AI companies have been charging a fortune while this existed.

100% open source. MIT license. 2K+ stars and climbing.

repo: https://t.co/7yTDGP6LmR

(Bookmark this before your next API bill arrives)

[mitte.ai @mitte_ai]

Want consistent characters in your Seedance 2 videos?

Create a character reference sheet first.

Here's how to do create and use them with Seedance 2, step by step 👇

[God's Way Foundation @godswayfoundinc]

Character consistency was AI video's biggest wall.

Seedance 2.0's native 4K + Nano Banana Pro just cleared it. Shadows, skin tones, edge detail, all holding up even in motion.

Look at the reference sheets below, then watch the shot. Bezalel, Sabaka, the whole camp. Every face locked to its reference across one continuous take, zero drift.

The sheet even maps his run: a red path tracing his route through the tents before he collides with Sabaka.

THE BOOK OF MOSES premieres Friday. 🌊

[Xor @XorDev]

Procedural generation will get a lot more interesting soon

[Reid Hannaford @reidhannaford]

Ok, this is absurd.

You can choreograph a complex action scene in Blender with basic shapes, then let Seedance make it real.

You need to try this AI filmmaking workflow:

1. Generate a start frame in Midjourney

2. Block out the action in Blender

3. Feed both to Seedance

My Blender reference was just rough timing, camera shake, and spatial choreography, and Seedance tracked the speed, motion, and action way better than I expected.

This is the difference between describing a shot and directing one.

[TomLikesRobots🤖 @TomLikesRobots]

First few tests with Seed Audio 1.0 from ByteDance and I'm loving it.
In initial tests voice acting and foley seems much better than native audio from SeeDance 2.
Also very cheap to experiment with. A 15 second audio test was only a couple of cents.
Definitely something I could integrate into my workflow.

[gokaygokay @gokayfem]

this is by far the most insane model i have ever played, it understands everything. just try it I am not exaggerating.

[Lovis Odin @OdinLovis]

Its coming tomorrow and no, its not seedance :), it should follow and respect much more the 3d input render, and its gonna be open source !

[Justine Moore @venturetwins]

Incredible to see what a professional animator can do with AI video.

He created a 3D previz and then had Seedance render the actual anime - with the motion and camera control preserved!

(made by @craftcapitallab)

[Santiago @svpino]

The architecture of this new world model is one of the most interesting things I've seen lately:

Let me first explain how most world models work:

They predict and render one frame at a time. If you are navigating in one of these worlds, and you look left, the model draws whatever looks right in the moment.

Every time you change your viewpoint, the model has to imagine what should be there again, so it's very common for these models to "forget" what's in the world. For example, if you put a toy on the table, look away, then look back, the toy might not be there anymore.

Tripo AI is releasing its Project Eden model, which works very differently:

The model builds the world first, and then renders it based on that map.

That map holds the real state of the world: the geometry, every object, where things are, what's already happened. The picture you see on screen gets generated from the map.

This architecture flips the whole thing. Now, you get the following:

1. The world stops forgetting. Leave, come back, and the toy is still on the table because it lives in the map, not in the last frame you saw.

2. You can edit the world, and those changes persist for anyone who enters later.

3. Multiple people and AI agents can coexist in the world and see it from different perspectives.

This is early research, but it's looking really promising. They just raised nearly $200M across two rounds to build it out.

Tripo will be at SIGGRAPH 2026 (July 19–23, Los Angeles Convention Center). If you work in 3D, embodied AI, simulation, or anything spatial, go connect with them there.

[A.I.Warper @AIWarper]

Workflow tutorial: Seedance ref videos to drive your animations

Disclaimer: Expect to hit moderation more than usual.

Details below in 🧵

[Unbound @unbound_io]

The loop is now closed! 🔄

Converting generated models back into SDFs unlocks additive and subtractive sculpting.

Edit > Augment > Generate > Edit again.

Then export to your favorite software with retopo and texture baking. ⬇ 💥

[Reid Hannaford @reidhannaford]

This is getting ridiculous.

You need to try this AI filmmaking workflow.

My Blender reference is embarrassingly simple. You can drive a precise multi-character shot with nothing but basic shapes.

1. Generate a start frame in Midjourney

2. Block out the scene in Blender with boxes, animate the camera

3. Feed both to Seedance

This feels like a real unlock. Your 3D reference doesn't need to look good.

[Zentrix⌚️ @ZentrixHQ]

📖SEEDANCE 2.0 IS SETTING A NEW STANDARD FOR AI FILMMAKING.

In a 20-minute video, you'll find out what you might not have guessed

With the right workflow, you can create cinematic AI videos with consistent characters, natural voiceovers, and professional-quality visuals.

The pipeline is simple:
• Nano Banana Pro for character sheets
• Multi-shot prompting for coherent scenes
• Seedance 2.0 for video + voice generation
• Topaz for upscaling
• Premiere Pro for the final edit

A repeatable workflow that works for AI short films, commercials, and client projects.

I found some good material that I have reviewed many times and decided to share with you. The author explains everything in great detail. This is not just a review - it is a pleasure.

📥Tomorrow I'm covering the one that surprised me the most this month.
🔖The guide below has some interesting information. One bookmark, one workflow, one result.

[Polsia @polsia]

Built an operating system for a UK agency that builds cinematic websites for barbers, mechanics, and local businesses. Every client should look like the authority in their market. That is the brief.

[Polsia @polsia]

Most startups die without a single outbound email sent.

LaunchDeck is the AI SDR that finds your leads, personalizes every message, follows up relentlessly, and books meetings — while you sleep.

No headcount. No agency. Just pipeline.

[Varchasva @Varcyyyy]

FIGMA MOTION IS INSANE!!

it took me just 4.5 seconds to make this

[Reid Hannaford @reidhannaford]

I'm blown away.

This AI filmmaking workflow for precise camera control, multiple characters, and dialogue is insane:

1. Generate a start frame in Midjourney

2. Match the poses in Blender, animate the camera

3. Feed both to Seedance

I didn't think this would work. Two consistent characters, solid performances, the move tracked perfectly through the entire beat.

Even the soup looks great.

[Allen Braden @allen_explains]

50 WEBSITES GOOGLE DOESN'T WANT YOU TO KNOW

1. 12ft. io — bypass any paywall
2. libgen. is — millions of free textbooks
3. sci-hub. se — free research papers
4. alternativeto. net — find free app alternatives
5. justwatch. com — find where to stream anything
6. archive. org — access any old webpage ever
7. gutenberg. org — 70K free classic books
8. pdfdrive. com — free PDF downloads
9. openculture. com — free courses from top unis
10. wolframalpha. com — solve any math instantly
11. photopea. com — free Photoshop in browser
12. squoosh. app — compress any image free
13. remove. bg — remove image backgrounds free
14. cleanup. pictures — erase objects from photos
15. unscreen. com — remove video backgrounds
16. carbon. now. sh — turn code into art
17. ray. so — beautiful code screenshots
18. shots. so — free product mockups
19. smartmockups. com — mockups without Photoshop
20. haveibeenpwned. com — check if you were hacked
21. virustotal. com — scan any file for malware
22. privnote. com — send self destructing messages
23. temp-mail. org — disposable email instantly
24. file. io — share files that auto delete
25. archive. ph — save any webpage forever
26. similarsites. com — find any site alternatives
27. radio. garden — listen to any radio worldwide
28. everynoise. com — explore every music genre
29. tunefind. com — find songs from any show
30. musicforprogramming. net — music to focus with
31. mynoise. net — custom focus soundscapes
32. coffitivity. com — cafe sounds for productivity
33. elicit. org — AI research paper assistant
34. consensus. app — search what science agrees on
35. connectedpapers. com — map research visually
36. semanticscholar. org — free academic search
37. scispace. com — understand any research paper
38. summarize. tech — summarize any YouTube video
39. phind. com — AI search for developers
40. regex101. com — test any regex instantly
41. codebeautify. org — format any code cleanly
42. jsonformatter. org — read JSON like a human
43. explainshell. com — understand terminal commands
44. raindrop. io — bookmark manager that works
45. downdetector. com — check if any site is down
46. tineye. com — reverse image search
47. fast. com — check your internet speed
48. smallpdf. com — edit PDFs free
49. ilovepdf. com — merge and split PDFs
50. 10minutemail. com — temp email in seconds

The internet is bigger than Google shows you.

Most people never leave the first page.