Artist, designer, pixel manipulator, exploring AI with childlike wonder π€ NFTs & AI art since 2021 π€ Minting on request
Joined March 2021
- Tweets 41,485
- Following 7,665
- Followers 20,524
- Likes 61,333
6,265 Photos and videos
Pinned Tweet
5 Mar 2025
π The latest piece made with director @paultrillo and amazing team at Asteria Film Co. - "Cuco β A Love Letter To LA" π
Making of video in the comments. β¨
Please cut to the end of the video for full credits!
π€π€ @FlippingSigmas @AIWarper
πππ
42
46
322
38,903
makeitrad retweeted
Jun 2
Martin Scorsese is an advisor to Black Forest Labs.
He's spent six decades shaping how the world sees stories. Now he's helping us shape visual intelligence with human taste and craft at the center.
We sat down with him for a working storyboarding session using FLUX.
298
295
2,573
2,620,236
May 14
Def worth a πβ¨
Just released LTX Director - An All-In-One Timeline Editor in ComfyUI. I2V, T2V, FLFF, Prompt Relay, Custom Audio, and more! Unlock LTX 2.3's full potential.
Hopefully it helps you create cool stuff easier!
2
7
454
May 13
WOW! This could be one of the coolest LTX 2.3 Loras yet! π₯π₯π₯
May 13
Introducing FLW, our first LTX 2.3 IC LoRA - designed to create seamless transitions between shots
Download link below β¬
1
7
809
Apr 30
Ohhhhh snap its about to crazy in here!!!
Apr 29
ComfyUI is the most flexible, composable, and powerful open-source media generation tool with a massive ecosystem of workflows and custom nodes.
Your Hermes Agent can now install, launch, manage, and run sophisticated @ComfyUI workflows on demand.
3
342
makeitrad retweeted
Apr 25
SDR to HDR from ComfyUI, I've trained a LoRA over Qwen Edit 2011 based on the principle used in hdr-lumivid.github.io/
A research I've had the previlige to work on with @noamiKenKorem for video HDR on LTX.
Links for the LoRA and workflow ( my fun grading node) below.
18
86
790
58,435
makeitrad retweeted
Apr 23
LTX HDR beta is now live.
Every AI video model before this one output 8-bit SDR only. Fine for social clips. The format falls apart the moment you try to grade. Highlights clip. Shadows crush. AI footage won't composite cleanly against higher-bit-depth CGI.
Resolution was never the real issue. Dynamic range was.
57
141
1,172
25,136,290
Apr 14
Could this be what we've all been waiting for??! π₯
Apr 14
Something big is coming.
AI video looks good until you try to use it in production. Our latest research on HDR video generation redefines what pre-trained models can do.
Stay tuned.
1
1
429
Apr 11
LTX 2.3, man... distilled. Ten seconds of video, 1080p, three minutes. Three minutes, man. That's... I mean, who does that? That's unreal.
LTX 2.3 by @Lightricks
Lebowski Lora trained on @ostrisai Ai toolkit
Dialog created w/ @NousResearch Hermes Agent
Im in love π€ sound on πππ
32
39
543
27,900
Apr 1
GmβοΈrning Wednesday, not the beginning, not the end. Kind of the sweet spot. πποΈπ΅
4
3
15
369
Mar 27
LFG we made it to Friday π€π₯
My brain needs a serious rest. I can't wait till 6pm π§ π«
3
6
34
628
makeitrad retweeted
I've been working on a Wan-2.2 LoRA based on one of my StyleGAN models. These things are so chaotic, even slight changes to prompts or params leads to wildly different outputs.
1
3
17
867
Mar 27
I'm late to the game on this one but if you haven't seen this you must watch π€£
I trained this @ltx_model LTX 2.3 LoRA of George Costanza at home on my 5090 in about a day with AI Toolkit. I generated this 30 second video with @ComfyUI on my 5090 in 6 minutes. Open source is, always has been, and always will be, the future of generative AI. (SOUND ON)
1
19
2,073
Mar 26
Gmπ’rning! π
Thursdays are for green!
Letting the palette do most of the talking today πΏ
14
4
25
404
Mar 25
GMorning Wednesday! βοΈ
We're half way there kids so close to Friday I can taste it π¦
12
3
28
454
Mar 25
This should be a good one. Hope I can sneak away from work for an hour β‘οΈβ‘οΈ
ποΈ LTX 2.3: The AI Film Studio - Deep Dive
π€ Hosts: Purz & Fill
β²οΈ March 25th β 3pm PST / 6pm EST
π Live on YouTube, X, and Twitch
We're doing a full deep dive on LTX 2.3 and testing every modality β text & image to video, first/last frame, and audio-driven generation.
1
273
Mar 24
Gm Tuesdayπ΄
Feels like everything got simplified in the best way. Playing with one of @araminta_kβs new LoRA's and letting the shapes do the work.
π and more examples π
5
3
14
455
Mar 22
Gmπrning Sunday. π
Itβs a sunny, hot one here in SoCal as I tinker with one of @araminta_kβs new WIP LoRAs. Clean lines, big shapes, colors doing most of the talking. Vibessss.
13
4
48
700