🎬AI Animation & Filmmaking VĂctor Sánchez Email me for comissions and professional video(ads, film, TV, social media, enterprise video) contact@voxelplot.com
Granada, Spain
- Tweets 928
- Following 622
- Followers 2,710
- Likes 2,864
Pinned Tweet
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
410
24,599
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
313
32,990
“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…
9
649
GPT-6 Astra + 3D Jutsu
I tested this workflow, and I am actually impressed by Astra's understanding of camera work.
It seems useful for certain scenes where you need to lock positions and camera movements very accurately.
The way to work with this is:
1. Use basic shapes: prisms, spheres and cylinders.
2. No details.
3. Do not add animations; only animate their placement in the scene.
4. Give each subject a different solid color.
Rendered in Seedance 2.5 at 480p.
When you add detailed elements like animations or geometry that accurately matches the subject, you don't give the model room to imagine, and it just renders directly on top of the scene's geometry.
2
7
64
4,045
Since I noticed in my last post that many people love dragon art, I decided to make a dragon animation...
(I summoned one)
5
29
1,735
I finally managed to create an Anime Fight Scene that looks straight out of a real TV show!
The latest AI updates and my recent research into animation pipelines are paying off massively, opening up entirely new techniques to explore.
Bringing this together required multiple layers and processes, but I’m thrilled with the final result.
19
65
632
17,042
If you don’t know what "LATENT SPACE" is, you’re missing one of the most important concepts behind AI Video.
Fortunately, Dr. Kit explains it in just 1 minute.
Watch this 👇
#DreaminaCPP @dreamina_ai
4
15
954
For the past three months, every single AI clip on my feed has been the same kind of chase scene:
one character running, riding, driving, or being chased by another.
It’s gotten to the point where, if I see a character running with the camera following them in the first second, I immediately scroll past, no matter what the actual content is.
Is this happening to anyone else?
3
7
695
Seedance 2.5 - Advanced Workflows Series
2. PREMIUM SAAS MOTION DESIGN COMMERCIAL
Seedance 2.5 is designed to get the maximum control out of it using references.
The prompt adherence is extremely good, and its "section-based" design style allows you to give specific instructions independent of camera, style, effects, and action.
Blur and light effects, animations with ease in/ease out timing—this model can handle it all!
I designed this entire commercial in about 5 hours without touching After Effects for a single moment.
Only art direction and artificial intelligence.
Workflow + Prompts 👇
13
26
1,345
5. Second Part of the Video
Now, since we have a fade to white, we can execute a dissolve effect from white to transition to the second part of the video. In my case, I extracted the transition to white from the first clip and reversed it to recreate the exact same effect and give Seedance the reference.
Afterwards, we will use the reference images to create the second part of the video in a single shot.
Prompt:
REFERENCE MAP: "img" = vid1 (dissolve effect, opening dissolve only) · "27373ff8-c74f-4979-863c-4894866fbae4" = img1 (pale-haired woman in iridescent clothing before a crystalline city) · "c409cd40-4c07-47b3-88dc-650c08456f68" = img2 (ornate silver and gold double-bladed crystal spear, on white) · "783dd18a-c4a2-4311-b5f2-a2b23e679ca8" = img3 (STYLE REFERENCE ONLY, NOT A FRAME: perfectly round water droplets suspended motionless in bright blue air, each throwing sharp starburst flares, dense bokeh field behind) · "b9306d6d-06ab-4b02-b0f9-2c2c3f27ff91" = img4 (STYLE REFERENCE ONLY, NOT A FRAME: faceted ice snowflakes, starburst flares).
CRITICAL RULE: img3 and img4 ARE NOT FRAMES OF THIS VIDEO. They are style references only, never reproduced, recreated or shown as a shot. Do not copy their composition, framing or camera angle. Every droplet and snowflake shot is a completely new, originally composed image built only in the spirit of those references. img3 and img4 are never shown full-screen and never appear as an image inside the frame.
Cinematic fantasy VFX commercial, Hollywood grade. 15 seconds. Celestial high-key world, strong white backlight, rim light, heavy bloom, prismatic flares, pale blue and silver-white palette turning to brilliant white-gold in the final act. DEPTH OF FIELD IS THE DEFINING LOOK IN EVERY SHOT: extremely shallow focus, wide aperture, only the subject sharp, everything behind it heavy creamy bokeh.
00:00-00:04 - Opens from white and resolves through vid1's dissolve. img1's woman appears in extreme close-up, fully out of focus, a luminous blur. A slow rack focus brings her to perfect sharpness while the camera pushes out and orbits slightly, widening to waist-up. The city behind stays deeply defocused. She appears once.
00:04-00:05:15 - She snaps her fingers and img2's crystal spear materializes floating in the air beside her, four metres long, glowing, arcane glyphs spiralling around it. She reaches out and takes hold of it.
00:05:15-00:07 - Gripping the spear she thrusts it toward the lens, tip aimed straight at camera. Very wide short focal length grossly exaggerating perspective: the tip and her hand loom enormous in the foreground, her face far smaller behind them. The camera dollies fast along the shaft toward her face. Barrel distortion, extreme foreshortening. She casts a spell straight into the lens.
00:07-00:08 - The spell becomes a beam of magical light rushing at the camera: a luminous white-gold shaft built from swirling particles and thin trails of golden smoke, sparks streaming along its length.
00:08-00:10:30 - The beam arrives in a field of perfectly round water droplets in the spirit of img3, hanging completely motionless in the air against luminous blue, each bead crisp and throwing sharp starburst flares, hundreds of them receding into a deep bokeh field. The camera sits inside this suspended cloud and orbits through it at normal speed, weaving between the still drops, parallax sliding them past one another. The magical light threads through the field, its golden particles and smoke curling around each droplet, wrapping them one by one.
00:10:30-00:12 - The light enters the droplets. Each bead ignites from within and turns brilliant gold, no longer water but liquid gold suspended in mid-air, glowing white-hot at the core, then hardens and freezes solid.
00:12-00:13:15 - The frozen golden beads shatter. At the instant of the burst the focus is thrown off completely: the golden snowflake stars in the spirit of img4 are never sharp, appearing only as heavily defocused shapes and glowing bokeh orbs scattering in slow motion across a fully blurred frame. From every burst a thread of white-gold magic escapes and streams outward through the blur.
00:13:15-00:15 - All the threads of golden magic converge and weave together, and the title is revealed out of that light against the already defocused field: bold sans-serif lettering reading exactly "SEEDANCE 2.5", spelled S-E-E-D-A-N-C-E, forming from brilliant white-gold energy with bloom and lens flares. The lettering is the only sharp element in the frame, razor crisp against a completely melted background of golden bokeh, held to the very last frame.
Style: fantasy, celestial, photorealistic VFX, god rays, backlit, lens flares, bokeh, slow motion, golden particle magic. Camera fluid, eased. 4K.
Made with AI
1
2
464
SEEDANCE 2.5 IS HERE!
Seedance 2.5 - Advanced Workflows Series
1. 30 Image References
Seedance 2.5 is here — now supporting up to 30 image references.
Animation quality has taken a clear step forward, with smoother motion and a much stronger ability to replicate Japanese 2D animation styles and their signature movement.
Prompts 👇
15
19
139
6,951
CAST:
"img1" = hero with teal spiked hair, red goggles, red scarf, torn white cape, conjuring spinning BLUE light discs.
"img2" = location.
Enemies: dozens surround him in a tight ring several bodies deep. Every enemy is one of "img3" to "img30", repeated through the crowd. No cuts inside shots.
SHOT 1 (7s) — BUILD-UP
Wide shot: hero small at center, enemies closing in from every side. Slow-motion dolly-in to his screaming face in extreme foreshortening, while the camera stays at full speed. Drift back to reveal the attack pose: arm pulled far behind, BLUE disc spinning in his fist. He whips forward and shoves the disc straight at the lens, action snapping back to full speed as it fires out of frame.
SHOT 2 (5s)
Orbit around "img3" as he dodges the disc. His body drops into slow motion, bending away as blue light grazes past, while the camera keeps normal speed, orbiting low and showing the miss from multiple sides. Dozens more enemies charge behind him.
SHOT 3 (7s)
The circle closes and dozens attack at once. Wide high-angle orbit descending into the fight: "img5" and "img7" swing and miss, the hero kicks "img9" away, elbows "img12", more bodies fly outward as "img13", "img14", "img15" and "img16" fold in to replace them. The orbit tightens until the camera is inside the brawl. The hero throws a punch directly into the camera in extreme foreshortening, ramping on impact.
SHOT 4 (5s) — FINAL BUILD-UP
Wide shot of the ring rushing him from all sides. Fast dolly-out with heavy VFX as he raises both arms, charging TWO BLUE discs. Forearms thrust toward the lens in extreme foreshortening while the body races into depth and the horde closes in. Smash into an extreme close-up of his furious face as he hurls both discs, camera violently orbiting off the release.
SHOT 5 (6s)
The discs rip away over the crowd and vanish into depth. Then a wide shot in three beats:
DETONATION — violent blue flash and shockwave blasting through the crowd, bodies thrown everywhere.
One full second of stillness.
The wave rolls toward the lens, with hand-painted anime dust and debris swallowing the frame.
SAKUGA LOCK:
Very wide lens, extreme foreshortening, limbs against the glass, body racing into depth. Dollys run along limbs and land on faces. Camera angle constantly changes: hip, worm’s-eye, high, side, close-up. Speed ramps affect either the launch or the impact/dodge, never both. Camera stays inside the fight, with bodies entering from behind the lens. Dust, debris and blue energy travel from deep background to the glass.
CAMERA STYLE:
LAGGING OPERATOR — always late, erratic and reactive. Hits land before the camera catches them. The camera jerks away from incoming bodies and recovers. Blows are thrown directly into the lens. HANDHELD only, never smooth, with constant shake, micro-corrections and violent jolts on impact.
IMPACT FRAMES:
Hardest hits flash one inverted negative frame, one normal frame, one negative frame, then normal. Deep dark blue shadows, brilliant white highlights, too fast to read clearly.
ANIMATION:
Japanese sakuga hand-drawn fight scene. One painted drawing per frame. 2020s high-budget TV anime compositing with heavy impact VFX. 24fps, animated on twos, hand-painted look, pose-to-pose timing, painterly boil, oil-brush texture and choppy stepped cadence. No interpolation, no motion blur, no morphing, no 3D and no CGI smoothness.
LIGHT:
High-contrast cel shading, deep shadows, rimlight, blue glow from the discs spilling onto faces and dust, lens flare with the sun behind. Never frontlit — always side or 3/4 backlight rimlight, golden hour, gritty, ambient occlusion.
5
712
Disney fired all its 2D animators, illustrators, and closed its 2D animation department in 2013.
The company that invented pencil magic killed its own legacy.
The paradigm shift actually started in 1995 with the massive success of Pixar's 'Toy Story', the first-ever 3D animated feature.
By the early 2000s, audiences were flocking to CGI hits like 'Finding Nemo' and DreamWorks' 'Shrek'.
3D became the shiny new standard, while Disney's traditional films like 'Treasure Planet' (2002) were massive box office failures that lost the studio tens of millions.
👇(1/4)
4
2
13
1,171
But this 2D revival was painfully short-lived. Lasseter championed 'The Princess and the Frog' (2009), a return to the classic musical formula.
While it performed decently, it didn't pull in the astronomical numbers executives now expected from the 90s Renaissance days.
Then, Disney essentially sent 2D out to die by releasing 'Winnie the Pooh' (2011) on the exact same weekend as the massive blockbuster finale of Harry Potter. It was completely crushed at the box office.
Meanwhile, Disney's new 3D films like 'Tangled' (2010) and 'Wreck-It Ralph' (2012) were proving to be highly profitable, massive hits. CGI was the safer bet.
👇(3/4)
2
3
233
By April 2013, the numbers dictated a cold, corporate verdict. Disney CEO Bob Iger publicly confirmed the studio had zero 2D features in development.
Quietly and without fanfare, the studio handed layoff notices to their remaining veteran animators—industry legends like Nik Ranieri and Ruben Aquino, the very masters who had spent decades breathing life into iconic characters like Ursula, Hades, and the Beast. The traditional animation department was completely dismantled. Efficiency and CGI profits won, silently bringing an end to nearly 80 years of unparalleled hand-drawn magic. 🎬📉
3
181