Most AI video work is just "generate and hope."
This is different.
Creator seungho__yeo ( IG ) rebuilt a live drum performance from the ground up.
Using the drummer's actual motion data to redesign background mood, lighting, and spatial depth frame by frame.
The pipeline:
→ Motion Tracking
→ Depth Mapping
→ AI Edit ( Seedance 2)
→ AI Relighting
→ Background Reconstruction
→ Cinematic Color Grading
All built inside ComfyUI.
This is what intentional AI production looks like. Not more generations, better direction.
This is the level ComfyUI creators are working at.
ComfyUI Yedp Action🤨 Director
3D viewport node to direct, preview, and batch-render 3D character animations, environments, and custom cameras for ControlNet workflows
-MoCap Sequences
-Facial Capture
-Multi-Pass Baking
-Animate multiple models etc
👇
https://t.co/rpplMjpbQE
@RonyVernet quando a menina esta sendo abduzida, corta pra versão dela adulta, que seria a jornalista. Acredito que o outro menino seja justamente o rapaz que consegue compreende-la
Hoy una industria entera dejó de tener sentido.
Un tío publicó en GitHub un repo que convierte cualquier foto en un mundo 3D explorable: meshes con físicas, splat del fondo, audio ambiente. Todo.
Una imagen entra. Un mundo sale. Cinco minutos.
La gente que se pasó diez años aprendiendo Blender lleva todo el día mirando esto en silencio.
Se llama image-blaster.
I've been experimenting a lot with using AI for game sprites.
It's not perfect - but with the right pipeline you can get quite far.
Been building a suite of tools to enable you to achieve game ready sprites using Images 2.0 & Nano Banana 2
Teaser of its capabilities below 👇
Behind the scenes of Milki Delivery looks INSANE🧠
Huge respect for the Milki Delivery team – sharing the actual workflow behind the game is super inspiring 🙌
Let’s boost more devs like this 💪
@DootWish #gamedev#indiegame#madewithunity
Live now.
Full step-by-step tutorial for getting REAL pixel art game sprites with AI
No more MIXELS!
> GPT Image 2.0
> Pixel Snapper by SpriteFusion
> Codex w/ GPT 5.5 High
> Phaser 4
Also how I solve other annoying bugs with AI generated sprites.
Prompts + more in reply👇
00:00 Intro
01:24 Overview of what we're building
02:42 Pick any AI tool
04:29 Problem 1: Fake pixels or 'mixels'
04:53 Problem 2: Frame Bleeds
05:39 Problem 3: Frame Drifts
06:21 Step 1: Generate a reference image
07:53 Step 2: Pixel Snap to Anchor
13:02 Step 3: Generate West-facing anchor
14:45 Step 4: Pixel snap (again!)
15:46 Step 5: Generating animation spritesheets
19:27 Steo 6: Recovering Frames
20:25 Step 7: Curating Frames
21:33 Step 8: Pixel Snap Each Frame
22:08 Step 9: Anchoring Frames
23:40 Step 10: Normalise and combine
26:28 Wrap up
A NEW AI VIDEO EDITING TOOL JUST DROPPED THAT WORKS LIKE A REAL VIDEO EDITING TEAM INSTEAD OF A CLIP GENERATOR
it's called agent opus and it's not one model doing everything. it's a team of specialized agents handing work to each other like an actual production studio.
you type a prompt, attach references (links, PDFs, images), pick a format, and they take it from there:
> @ researcher pulls facts from your URLs and docs
> @ scriptwriter drafts the transcript
> @ storyboardartist breaks it into scenes
> @ hookdesigner generates 3 viral hooks for you to pick from
> @ assetmanager collects the visuals
> @ motiondesigner builds the animations
> @ voiceactor handles narration
> @ videoeditor cuts the footage and polishes timings
you stay in the loop the whole way. it shows you the plan, waits for your sign-off, lets you pick the hook, then assembles the final scenes.
prompt box options: vertical format, voice, AI twin, and style match (so it can copy an existing video's look).
the bigger picture: the multi-agent pattern that took over coding tools (claude code, codex) just landed in video production. each agent owns one role and only its role.
the real read: the bottleneck for AI video was never the clip generation. it was the research, scripting, hooks, and editing decisions. agent opus is the first tool that breaks those into named specialists instead of stuffing them all into one bloated model.
link in replies 👇
New tutorial: MetaHuman x FaceBuilder for Blender
A step-by-step guide to a faster way of creating a photorealistic MetaHuman from photos. Head generation from images, texture work, and character customisation – all in there.
Full video: https://t.co/mmRhF5kvRb