🎬AI Animation & Filmmaking Víctor Sánchez Email me for comissions and professional video(ads, film, TV, social media, enterprise video) contact@voxelplot.com
Granada, Spain
- Tweets 929
- Following 622
- Followers 2,717
- Likes 2,874
This is a good example on how AI really works in the Art field.
People who benefit the most are the ones with expertise and understanding of both technical and strong artistic fundamentals.
The most important skill when using AI:
Knowing when and were NOT using it.
People is already vibecoding small Apps adapted specifically for a person, programming shaders, previs tools, rendering, etc...
Herramienta procedural de generación de edificios estilo Brutalista.
Houdini y Astra es lo que he utilizado para esto. Tengo tanto, pero TANTO que decir.
Esto SI me parece un cambio de paradigma total, los pocos errores que hay son de antes de lanzar el render, ya están solucionadas algunas intersecciones al mover la estructura de los monorailes y ni siquiera eran un problema ya que sólo vale con ajustar ciertos parametros para evitar algunas colisiones.
Puedo perfectamente seguir puliendo y escalando, obviamente ahora no está pensado para que se vea en planos cercanos (O si, con IA rendering) sino más bien para generación de multitud y fondo par a rellenar planos a lo bestia.
La forma correcta de trabajar con estas herramientas es poniéndote tú como supervisor o director y no cómo artista, estas dirigiendo y no creando.
La barrera técnica ha caído en estos ejemplos se ha desplomado a unos niveles que aún no podemos imaginar, y ya sabemos que estos modelos no hacen más que mejorar y pronto serán más rápidos y precisos. Esto no es trabajar en espacio latente, es aplicar matemática pura en tu programa y obtener resultados extremadamente precisos.
Las posibilidades son infinitas de aquí en adelante. Pero tu conocimiento juega un papel fundamental, es muy difícil que gente sin experiencia pueda competir contra seniors utilizando esto.
Por supuesto esto abre todas las opciones a creación de animáticas, videojuegos, cortos CGI.. creo que aún no somos conscientes de lo que suponen estos modelos, todas las miradas estaban en la generación de vídeo y espacio latente, pero nadie ha visto venir esta aplicación en programas tradicionales, por supuesto de aquí en adelante solo queda ver como se mejoran solvers y herramientas de una forma que antes era difícil de imaginar.
211
Plot Twist: 2D animators start to get hired to produce 3D films by big majors and instead of AI replacing them it makes them be more demanded
(I think this will happen, actually)
What if AI could help bring the golden age of 2D animation back to cinemas?
I brought this incredible pencil test by legendary Disney animator #MiltKahl for Pinocchio to life using AI.
There’s something really special about seeing these rough drawings come alive with a 3D look. And I think that’s where AI could become genuinely useful for animation: letting animators focus more on acting, timing, and motion instead of polishing every tiny detail, like the eyes or nose, as you can see in the rough pencil test used here.
AI won’t replace 2D animation. It could help bring it back to the big screen (or Netflix).
#Seedance #Dreamina
30
15
314
33,092
El criterio no es técnico: la etiqueta de IA debe ponerse solamente si es susceptible de herir el ego de un número suficiente de personas.
EJEMPLO:
Programador = Freak = Tus habilidades no valen nada
100% de programación en juegos es asistida por IA>> Ni etiqueta IA ni h*st**s
0 egos heridos > Etiqueta Innecesaria
36
Your work is one of the most interesting I see in AI space. Thanks for making these test and share results!
1
1
64
You have a lot of line boiling and small subtle flickering/aspect ratio changes in the original.
Also your sketches have shading baked and small details that real 2D Animation avoids specifically for the same issues you are facing.
It seems to me that if fix these things and provide Genga-style layouts the output will look much better.
The issue is input, not output.
1
1
1
216
Have you created any famous movie of your own authorship?
Have you created any famous show of your own?
Are you a person with a relevant cultural impact?
You should measure yourself by the same standard you use for others before going after them.
In any case, many of us artists DO NOT CARE AT ALL about everything you are pointing out.
2
11
809
“Klaus” (Academy Award-nominated) used AI to infer consistent 3D surface information from hand-drawn 2D animation.
As Sergio Pablos explains, the key problem is surface correspondence.
The system must track the same point on the character across different drawings.
This creates something similar to a persistent UV map over 2D animation.
Once that exists, textures, lighting and other surface information can follow the character’s volume without using a fully animated 3D model.
AI could reconstruct fake 3D passes directly from 2D drawings:
• normals
• depth
• position
• material masks
• UV / surface correspondence
Those passes could drive lighting, shadows, materials and FX while preserving the original 2D animation.
Pipeline:
✦ Original 2D animation
⬇ AI-generated textures
⬇ Reconstructed 3D passes
⬇ Lighting / shading / FX
It is almost the inverse of Arcane:
3D → made to feel 2D
Instead:
2D → given the depth and material richness of 3D
What concerns me most is that artists who are open to AI-assisted workflows can face harassment or backlash, making some afraid to collaborate even when they are interested.
I really hope this changes over time.
I'm particularly interested in workflows involving:
• color transfer
• rendering and relighting
• illustrated texture transfer
• AI-assisted compositing
• hybrid shots combining hand-drawn animation and generated elements
• sequences mixing traditional / handcrafted shots, • hybrid shots mixed fully generative shots in final animation
This is the link for the full interview with Sergio Pablos:
dailymotion.com/video/x7rcg1…
10
663
It does not relate what's studios vision about AI and the fact that an individual can create AI Anime alone with a quality enough for people not be thinking only "this looks like AI"; something thay is actually happening.
Even on youtube and social media people is starting to get interested in the Universes, stories and characters of solo creators assiested by AI.
We are not competing with major studios, we are creating just an alternative to Executive drived enterntainment, where the focus on the MESSAGE is set by the creator itself
5
319
In Japanese animation, lipsync does not follow specifc phonems, so you have to fit sentences instead of syllabes.
That makes easier to fit good voices, as you only have to stretch frases and, if you have already a gen, you can tag exactly how long it will last:
Example: "I think..." (00:00:00-00:00:10); pause 1s, (00:00:10-00:01:10) "..its ok" - (00:01:10-00:01:37)
I am using Seedance to generate voices as It has better performance than any voice model tested, by far.
To avoid SFX, NO MUSIC, NO SFX and I use a setting in the scene that has no sound. like atmospheric reflexion, off voice, character thinking, quiet empty room, character sitting, etc
That way you get a clean voice.
6
512
With Wan 3.0 AI anime is getting seriously close to TV quality.
You can create sequences like this one that look like an actual seasonal anime.
I made a full fantasy fight between a Mage and a Swordswoman — and it genuinely feels anime-ready.
Seedance 2.5 keeps characters more on-model. Wan is better at timing, poses and complex layouts. Hailuo H3 sits in between.
All three support Vid2Vid and Omni Reference, so you can pass shots and references between them.
The possibilities are endless. Interesting times.
36
33
412
24,887