@OffworldAndre

VFX guy doing AI stuff, pushing pixels, Creator @heyglif

Joined June 2024
  • Tweets1.6K
  • Following119
  • Followers128
867Media
My name is Schnitzel, Werner Schnitzel
33
3
62
youtu.be/U6fGmNcn6zA. Updated YT version with fixed AR of yesterday's vid. It was generated in glif and then my agent uploaded it here and Discord. Ffmpeg has no image vision and it wrong. Was just an experiment

When taking a photograph

created with glif.appseedream 5.0, grok video and elevenlabs

youtube.com
1
77
2
48
1
2
58
1
43
2
37
3
43
3
49
Tengo que decir que lo mejor que he descubierto esta semana es poder usar esta voz desde ComfyUI para hacerme toda la documentación de mis nodos. Me lo estoy pasando como un crío creando estos mini tutoriales 😂
3
6
105
4,526
For me this totally YES WAY!!!
Max ✦
@MaxVOAOJul 23
NO WAY!!!
2
52
2
45
1
37
2
61
👋🏻 Adios al dolor de cabeza al mezclar 3D y VFX con IA en @ComfyUI Ya tenéis disponible NKD VFX Tools, un pack que recoge muchas de mis herramientas para workflows híbridos sin salir de ComfyUI. Lo mejor de los dos mundos: control de luz, cámara y perspectiva gracias a las técnicas "tradicionales", pero implementadas con un enfoque moderno en un entorno IA.
26
99
1
823
55,292
srolkk retweeted
GLIF
@heyglifJul 22
Watch Glif narrate how it's building a short form version of Odyssey in "Diorama" style. This is one of many "skills" in Glif, and you can teach it your own formats 1. Build something in chat, using 100+ AI models (from Flux to Seedance) 2. Tell it to lock it in as a skill!
4
4
1
8
2,485
1
40
The Settlers AI edition. (Don't go to any of those tiles)
4
58
srolkk retweeted
Ostris
@ostrisaiJul 20
Added a validation loss for AI Toolkit (red line). You can select 1 or more images/prompts to use for validation. This is a deliberate overfit run I did on a character of 19 images, 1 validation image. This makes the graph have some actual utility.
8
8
111
5,912
srolkk retweeted
GLIF
@heyglifJul 21
Glif can now inspect its own outputs and self-correct when it finds issues - just tell it to use the verification skill! Here, it takes a model, an outfit and a simple prompt as inputs, generates, self-corrects and only then puts together the final multi-scene video...
4
2
1
15
3,273
Load more