VoxelPlot

448 posts

VoxelPlot banner
VoxelPlot

VoxelPlot

@voxelplot

✍️ Illustrated and Animated Microfiction 👁️ Creating worlds where tech meets narrative 🎬 AI Animation & Narrative Art

Granada, Spain 参加日 Nisan 2013
380 フォロー中194 フォロワー
固定されたツイート
VoxelPlot
VoxelPlot@voxelplot·
I’ve finally applied #ViduQ3 to a narrative project for @SquadBlastgame . It handles action sequences and explosions with a level of consistency I hadn’t seen before. I achieved camera movements I’ve had in mind for a long time that other models simply wouldn't allow me to implement. The Start-end frame option generates high-quality animations with great control, provided you choose the points wisely and give the model enough time to generate the full movement fluidly. Grok surprised me with its iteration speed. I use it to bring dynamism to establishing shots and dialogue scenes that require quick corrections. If the scene needs movement, it’s my first choice. For more paced scenes or dialogues in wide shots, I prefer Sora 2. It is better suited for maintaining character style in distant shots, where Grok tends to struggle. The music was created in Suno (Industrial Tech-Step). I was looking for a sense of movement through minor-key synth arpeggios and extreme reverb. The "Studio" feature allowed me to precisely control the intro length and the exact point where the kick hits. Finally, a huge thanks to @Framer_X for the amazing work on Cartoon Hero and for helping me connect with the professional world, and to @Artedeingenio for his SREFs. I didn't have much time to develop the art style from scratch, so I used one of the SREF he shares. It fit perfectly with the bluish palette and the Otomo-inspired retro sci-fi style I was aiming for. It easily saved me a full day of work. IF ANYONE HAS ANY TECHNICAL KNOW-HOW QUESTIONS RELATED TO ANY SEQUENCE FEEL FREE TO ASK IN THE COMMENTS.
English
32
10
97
10.3K
VoxelPlot
VoxelPlot@voxelplot·
@Ezeqi_ @durincoffee @Fe_Saibot @JuniXx10 @lashingiris Parece que estar sentado dibujando no requiera esfuerzo. Al que lo dude le sugiero que se siente a dibujar 8h efectivas (sin contar descansos) durante 7 días seguidos y luego me cuente cómo tiene el hombro, la espalda y el cerebro
Español
0
0
0
38
Ezeq!
Ezeq!@Ezeqi_·
@durincoffee @Fe_Saibot @JuniXx10 @lashingiris Ok, 1 semana, jornada laboral de 8 o 9 horas al día dibujando durante 7 días, 4 segundos de animación 1000 dólares. Sí, para estar sentado en su casa dibujando y como dije; el doble de salario mínimo, es mucho.
Español
25
0
82
37.3K
VoxelPlot
VoxelPlot@voxelplot·
@JuniXx10 Se anima en doses, es decir 12 fotogramas por segundo. Serían 12 dibujos coloreados, a 20$ el dibujo. Habría que ver si hace fondos también o solo personaje Me parece muy bien el precio, el trabajo de animador es muy variable y los precios deben compensar la irregularidad
Español
0
0
0
28
yachimat - AI Short Anime
yachimat - AI Short Anime@yachimat_manga·
こんな感じでした。いろいろやってるように見えますが、実はこのアニメのインプットは巨大なYAML一つ。 2時間のチュートリアルでしたが、参加者のみなさんはもう使いこなせてると思います!
yachimat - AI Short Anime tweet media
日本語
1
0
13
811
yachimat - AI Short Anime
yachimat - AI Short Anime@yachimat_manga·
即興アニメ 「リク東京いくんだって、もう決まってるっぽいよ?」 ////////////////// 昨日の @TapNow_AI のワークショップのハンズオンで即興でつくったアニメのシーンです。 大体30分くらいだったので背景やテンションの一貫性とかはご容赦を リプ欄にワークフローのスクショもおいておきます お題としては会話劇。 ・会話っていうのは相対して話させるよりも動作の中で(今回は歩かせる) ・主人公は左から右に向かう、イベントは右からくる ・時間帯や天気と感情は揃える みたいな基本を盛り込みたかったのでこういう感じにしました で、これ見てると気になるところ結構あると思います 背景とか光とか、そもそもリク追い付いたって言ってるけど前から来てないか?とか こういう修正をするのが動画生成のメインですよね ワークフロー型だとそれが整理しやすいし便利だし早いよね、っていう話をしていました!
日本語
4
7
71
3.7K
VoxelPlot
VoxelPlot@voxelplot·
@MetacoGen If you take a step let me know, there is a tiny variation from the video of youtube i postes in order to do the style transfer to video
English
0
0
0
17
MΞTΛCO
MΞTΛCO@MetacoGen·
@voxelplot Stunning! This is really beautiful and unique. Also definitely a workflow I’d love to explore
English
1
0
1
15
VoxelPlot
VoxelPlot@voxelplot·
Pain, grief, longing. I used AI to create an animated oil painting short film about grief and the loss of a loved one. It features the art style of the renowned Spanish painter Joaquín Sorolla, with a great flamenco song of Astola y Ratón - "Cojo el saco y me retiro". It’s an animation style you hardly ever see because of the sheer complexity of painting every single frame in oil. Set in a mediterranean village, it follows a man longing for his wife on the anniversary of her passing at sea. One thing I love about this short is that, despite using AI, the video model wasn't actually trained on oil painting animations. Meaning: the AI isn't just replicating an animation or copying an existing style. I used USO (Unified Style and Subject Driven Generation via Disentangled and Reward Learning, Bytedance) to transform the style frame by frame. One of the main arguments against generative AI is that it's just used to "plagiarize" other people's work and is incapable of generating truly original art. Well, for this video, I combined several AI tools that let you isolate specific image and video elements. This allowed me to generate an animation in a completely new style—one the AI itself was never trained on. Soundtrack - Astola y Ratón - "Cojo el saco y me retiro": Spotify: open.spotify.com/intl-es/track/…
English
7
2
16
239
VoxelPlot
VoxelPlot@voxelplot·
@hippieh0p Than you! I am thinking lf exploring this style translated to anime
English
0
0
0
7
VoxelPlot
VoxelPlot@voxelplot·
@horacedodd Thank you Horace!! Hope some day I will reach your level 😉
English
0
0
0
13
VoxelPlot
VoxelPlot@voxelplot·
@masterdiverhrsh Well it ks a bit technical, but once you know the basics you have a lot of room to improve and explore. I had to modify a workflow posted in this youtube video to get the result: youtu.be/co8g61in4qg?is…
YouTube video
YouTube
English
1
0
1
26
VoxelPlot
VoxelPlot@voxelplot·
@masterdiverhrsh Yeah! It is a bit technical though, I used comfyui. First: videos generated with Kling 3.0 Secong: transfer style frame by frame in comfyui with flux and USO adapters (bytedance) Have you used comfyui before?
English
1
0
1
55
Harsh Shekhawat 🇮🇳
Harsh Shekhawat 🇮🇳@masterdiverhrsh·
@voxelplot Wow! Love it man, would genuinely love to remake. Could you please share a post on how exactly you did it?
English
1
0
1
35
VoxelPlot
VoxelPlot@voxelplot·
@AIWarper How can you apply this to generations? can you guide video or image gen (with controlnet)? compatible with sd based checkpints and flux?
English
1
0
0
233
A.I.Warper
A.I.Warper@AIWarper·
DVD - Deterministic Video Depth Estimation with Generative Priors Pretty decent output given such a difficult input. It functions on windows as well so it dealt with the scene cuts quite well
English
4
15
126
8.4K
VoxelPlot
VoxelPlot@voxelplot·
@guhki1004 I love the acceleration of the camera, really good work
English
1
0
41
20.7K
guh ki
guh ki@guhki1004·
Animation I made last year
English
95
1.6K
20.8K
1.5M
VoxelPlot
VoxelPlot@voxelplot·
Souces report Bytedance has suspended te release of Seedance 2.0 We will have to access through expensive APIs, resellees or rent a chinese number to register in the chinese apps directly. reuters.com/technology/byt…
English
0
0
0
168
VoxelPlot
VoxelPlot@voxelplot·
@yachimat_manga Would be great if you do the tutorial you did the last time in english
English
0
0
1
75
yachimat - AI Short Anime
yachimat - AI Short Anime@yachimat_manga·
TapNowでのチュートリアル定例開催していくんですが、来週以降の企画はまだ考え中です とりあえず考えてるのはカットインとか普通編集でやるよなやつを生成でやっちゃう系です 他に何かリクエストあれば教えてもらえると非常に助かります!初心者向けとかでもどのへんで詰まるのかとか教えてほしいです キャラデザでもいいですし、背景とかカットの繋ぎとか… 話したいことは色々ありますが、どこに需要があるのかがいまいちわかっていません @TapNow_AI
日本語
4
16
137
9.3K
VoxelPlot
VoxelPlot@voxelplot·
@javilopen And how visibility depends on algorithm rather than quality
English
1
0
2
56
Javi Lopez ⛩️
Javi Lopez ⛩️@javilopen·
This made me realize just how insanely important content localization is. I posted it on this account too and it totally flopped, less than 200k views across two tries. Which makes total sense, because it's in Spanish and features people you guys don't even know.
GIF
English
6
0
15
2.4K
Javi Lopez ⛩️
Javi Lopez ⛩️@javilopen·
OK, I'm in the Spanish news after my short hit 9M views on my ES account. 🔥 NINE MILLION VIEWS 🔥 It's the "Apex" moment of Dor Brothers but for Spain & Latinoamerica 😀 Now let's create a huge viral one for US market!
Javi Lopez ⛩️ tweet media
English
20
4
178
11K
VoxelPlot
VoxelPlot@voxelplot·
@hectorVFX Tienes algún workflow para automatizar modelados 3d de forma atomática (con formas básicas, blockout) a partir de imágenes, con IA? Me refiero a escenarios
Español
0
0
0
22
hectorvfx
hectorvfx@hectorVFX·
Miguel Arribas es el que esta haciendo todo este development, una autentica bestia y una pasada poder contar con el para investigar todas estas herramientas 🔥
Español
1
0
7
653
hectorvfx
hectorvfx@hectorVFX·
Worfklows de Houdini + ComfyUI que estamos preparando🙂
Español
5
13
218
5.9K
hectorvfx
hectorvfx@hectorVFX·
1. Generación de imágenes y vista múltiple de personajes (Multiview) en ComfyUI. 2. Modelado y texturizado de vista múltiple con ComfyUI Trellis2. 3. Rigging en Mixamo. 4. Animación (Crowds) en Houdini. 5. Houdini Flipbook, layout (Los cilindros de gas estaban en el layout original, pero no aparecen en la captura de pantalla), cámaras, etc. 6. Render con IA utilizando la tecnica skyreel de Mick Mumpitz
Español
5
1
36
1.7K