Mark DK Berry

Focused on AI visual story-telling using open source AI tools 🇦🇺

[Mark DK Berry @MarkDKBerry]

I post all my latest AI workflows and tutorials on Patreon (free tier) https://t.co/0nVs1pDsFJ

[Mark DK Berry @MarkDKBerry]

After several days in Hell, BSOD resolve and new memory approach for ComfyUI came with it from the struggle. I call not "spending on new hardware" a definite win. https://t.co/3wdfB9e1cF

[Mark DK Berry @MarkDKBerry]

They bring the low hanging fruit down to meet us as time goes by

[Sudo su @sudoingX]

cancel your chatgpt subscription for a month. buy a single used 3090, call it a grand. run qwen 3.6 27b dense on it and let it grind on your actual work, the code, the drafts, the boring research.

here's what happens. you go the whole month and barely hit a wall. the few times you do, you clock that THAT's the 10% you actually needed the frontier for, and the other 90% a card sitting in your room handled just fine.

most people pay every month for capability they touch a handful of times. own the 90%, rent the rest only when you hit the wall. trust me anon, you won't look at that subscription the same again.

[Mark DK Berry @MarkDKBerry]

@sudoingX I h ave a theory that if I hold onto my 3060 long enough it will become good enough

[LTX.io @ltx_io]

Check out what our team created with the new LTX Trainer! 👇

Water Simulation
Add rivers, surf, rain, floods, or splashes to any shot while preserving composition and motion

(1/10)

[Mark DK Berry @MarkDKBerry]

The "emotion" in dialogue and character facial expression or action is the "holy grail" of film making but is it possible with AI yet? https://t.co/qVQpaXZcUa

[Mark DK Berry @MarkDKBerry]

5-Min How-To: "Batch from AIMMS" custom node. This is for use in ComfyUI running batch shots from a CSV or from AIMMS storyboard management database. https://t.co/cF74QZyRkp

[Mark DK Berry @MarkDKBerry]

TripoSplat & QWEN w. Lora - Move To Any New Camera Angle Fast. This is the fastest way I have used so far to get to any new camera angles quickly from an 2D image of any scene in ComfyUI. https://t.co/CNssn1C8MN

[Mark DK Berry @MarkDKBerry]

Dialogue Scenes - Part 2: "Where The Rubber Meets The Road" (LTX 2.3) https://t.co/W9eYgIOIM9

[Mark DK Berry @MarkDKBerry]

please dont go closed source

[LTX @ltx_model]

World models are the next frontier.

We're partnering with @NVIDIA's Cosmos Coalition to help build and open-source them, alongside some of the best AI labs in the world.

More at GTC Taipei.

[Mark DK Berry @MarkDKBerry]

AIMMS license, and PiD, a new image to 4K booster is worth checking out. https://t.co/HgYkQjV2mW

[Mark DK Berry @MarkDKBerry]

5-Min How-To: Using "Prompt Relay" For Multi Character Dialogue (LTX 2.3)

This video discusses using prompt relay for multi-character dialogue scene. What works, what doesnt, and the approach I will use with it in future. https://t.co/IYC19ZoS1x

[Mark DK Berry @MarkDKBerry]

@NousResearch all greek, init

[Mark DK Berry @MarkDKBerry]

@NousResearch her (her) mees (knees)

[Mark DK Berry @MarkDKBerry]

LTX 2.3 in ComfyUI - Dialogue scenes and how I approach making lipsync using audio to drive it. This is detailed explanation of the approach including the workflows I use. https://t.co/PuKzZenTrf

[Mark DK Berry @MarkDKBerry]

using #VibeVoice and #Audacity to create 10 second audio clips timed to perfection. Also provided is the fix for mouth movement failure in #LTX 2.3 #lipsync when short audio is used for dialogue in #ComfyUI https://t.co/cZItZ5DBsH

[Mark DK Berry @MarkDKBerry]

This is the main LTX2.3 v2v workflow I use that is part of the "video pipeline workflow" set you can download from the link. #comfyui #ltx #video2video https://t.co/V2srwzbMbv

[Mark DK Berry @MarkDKBerry]

Music video of "Been Down", the opening music track from "Black Magic: The Musical" . all ComfyUI workflows used to make it are included https://t.co/p9vaaBRpe6

[Mark DK Berry @MarkDKBerry]

If you wonder why people say Klein is the best but you dont get good results. I was the same. This fixed it. I am now a believer. #klein #qwen #comfyui https://t.co/e5qGcScIxf

[Mark DK Berry @MarkDKBerry]

5-Min-How-To - Batch From CSV - Multi-Character Portrait Detailing #comfyui #zit #QWEN https://t.co/Uktvc7n9JD

[Mark DK Berry @MarkDKBerry]

Batch Processing Text-to-Image in ComfyUI Using CSV & AIMMS Storyboard Manager https://t.co/xFdkDWRSB9