ChatGPT
Perplexity
Claude
Gemini
Comment Mile 80 utilise OpenArt pour multiplier massivement sa production, et ce qui devient possible une fois le flux de travail transformé
Pour Ryan Sheffer, la relation avec OpenArt a commencé avec une fonctionnalité qui faisait le gros du travail. « La fonctionnalité numéro un qu'on a utilisée le plus longtemps, c'était image de début, image de fin, faire une vidéo », dit-il : générer la première image d'un plan, générer la dernière, et laisser le modèle remplir le mouvement entre les deux. Aussi simple que cela paraisse, c'est ainsi que le studio de Sheffer, Mile 80, a discrètement mis des plans générés par IA au service de certaines des marques les plus reconnaissables au monde. Sur un récent show BMW, Mile 80 a livré des vidéos pour Mini Cooper et Rolls Royce, et selon Sheffer, la plupart des contenus liés à BMW cette saison-là comportaient au moins un plan généré ou partiellement généré avec OpenArt, le genre de clients haut de gamme, selon ses mots, « dont on ne penserait pas qu'il y a de l'IA dans leurs vidéos ».
Sheffer founded Mile 80 nearly a decade ago after years of working as what he calls "the nerdy guy" in post-production and visual effects. The studio built its name in live events: 360-degree screens, spatial storytelling, the kind of shows where a single project might need hundreds of assets rendered at 30K resolution. It's a business built on technical difficulty, and Sheffer has spent his career finding the next hard problem before everyone else does. That instinct is what brought him to AI early, and it's also what makes him refreshingly honest about where it actually helps.
Pourquoi les images de début et de fin ont tout changé
Sheffer s'est assis avec nous pour raconter ce qui s'est passé une fois que son équipe a cessé de traiter OpenArt comme un simple générateur autonome pour construire autour de lui.
The shift came when OpenArt opened up its MCP server. Mile 80 began layering its own interface on top, using Claude to manage the entire creative process, from building shot lists to critiquing individual frames, and routing the actual generation requests to OpenArt underneath. "We've started like putting UI on top of it," Sheffer explains, "basically we're only building now with Claude, which is very interesting. So our UI is Claude for OpenArt these days."
In practice, that means Mile 80's artists talk to Claude the way they'd talk to a coordinator on a physical set. They define characters, environments, and reference images, then Claude builds what Sheffer calls a production bible and shot list, and routes generation requests to OpenArt for the actual start and end frames. Two of his artists, Camila and Francez, built a custom Claude skill that takes a script, breaks it into individual shots, and fires off the OpenArt requests automatically. "It works really well," Sheffer says.
One of the pieces Sheffer is proudest of is a Rolls Royce animation Mile 80 built entirely with OpenArt-generated frames, the kind of luxury-brand work he says has no real precedent for AI involvement. "I can't think of a brand that is higher end than that," he says.
OpenArt's contribution here goes beyond just start and end frames. Rather than generating a finished background, Mile 80 prompts OpenArt to build visuals with a green screen already baked into the shot, then relies on its own compositing tools, the same ones it's always used, to pull that green screen out and layer the shot into the scene. It's the detail that lets Sheffer's team keep working the way a VFX shop always has, just with a generated element standing in for what used to be a live-action plate. The same approach produced a character Mile 80 built for LangChain, an animated figure named Newton generated with a green screen baked in and then composited out, set to appear as part of a New York City subway campaign.
Le projet qui aurait dû être impossible
The clearest example of what that pipeline makes possible is Gammarama, a live event series the client wanted positioned as something like the new TED talks: more serious than the brand's usual output, without losing its sense of fun. Sheffer's team had five weeks to develop the entire visual identity and then deliver on it. "There was only five weeks to develop the entire visual identity," he says, "what the deliverables would be, each of the video scripts, each of the videos, storyboards, and then execute and deliver for a large screen display."
Sheffer is direct about what that timeline would have meant without an AI-based pipeline. "It would have absolutely been impossible," he says. « On n'aurait jamais pu accomplir ce qu'on a fait. » L'équipe aurait dû revoir le concept à la baisse, vers quelque chose de plus simple et de moins marquant, juste pour respecter le délai : moins de styles visuels mélangés, moins d'éléments animés à l'écran, quelque chose de plus proche d'un montage classique que de l'identité stylisée et en couches que le client a finalement obtenue. Il attribue à son animateur principal, Fran, le mérite d'avoir fait progresser les workflows IA de l'équipe suffisamment pour rendre possible cette version ambitieuse.
What made the timeline work wasn't a single clever trick so much as the team's willingness to treat "if this were possible, how would we do it" as the starting question, rather than "can we even attempt this." Green screen and alpha-channel generation handled the layering, while Claude, connected through MCP, handled direction and shot management. And because OpenArt could turn a concept into a usable start and end frame quickly, the team could iterate on a look before committing real production time to it.
La différence entre le soin et le bâclé
Sheffer's read on generative AI is more particular than the average AI-optimist take, partly because he's been burned by the hype cycle before. Back in 2013, before founding Mile 80, he ran a company that automatically generated short news videos from trending social posts, pulling content based on hashtag and location spikes and stitching it into a reel with an early large language model. It worked, in the sense that it got views. It also produced, by his own account, a video about a viral photo of a slice of pizza at the World Series that did numbers, and that was the moment he started backing away from the business. "I did see AI slop immediately as the core issue," he says. "That's funnily enough kind of why Mile 80 was started."
That history is why he's specific about what AI tools are actually good for. "The generative AI tools are the world's fastest, and in some ways dumbest, employees you have," he says. "You have to be incredibly specific with what you ask for. And if you correctly ask them for it, they will give it to you." He compares the goal to how David Fincher uses visual effects in nearly every shot of every film he makes, so seamlessly that audiences never register them as effects at all. "No one thinks of him as a visual effects director ever," Sheffer says. "Why? It's so good. It's integrated into the scene." The alternative, in his view, is the same failure mode people associate with the least-liked Marvel visual effects work: technically present, but not actually serving the story. "That's the same thing as AI slop," he says. "It's not understanding how to use the tool."
Il est tout aussi clair sur la limite qu'il s'impose à lui-même. « Je ne veux jamais avoir un accès API à OpenArt pour générer cent mille vidéos d'une banane qui raconte une blague », dit-il, et ce n'est pas qu'une plaisanterie : la génération de masse, sans garde-fou, c'est exactement le scénario catastrophe qui a coulé sa précédente entreprise.
Plus d'ambition, même échéance
Sheffer ne cache pas ce que la génération plus rapide apporte vraiment à Mile 80 : pas plus de clients, mais des projets bien plus ambitieux dans les délais qu'ils ont déjà. « J'ai constaté que c'est plus rapide, dit-il, mais le projet qui aura désormais Godzilla n'avait pas le temps de faire Godzilla autrement avant. Ta capacité à passer de l'idée à la visualisation est bien meilleure. » Un concept qui autrefois aurait été discrètement simplifié pour tenir dans un délai peut désormais rester aussi ambitieux que le brief l'exigeait vraiment.
La seule contrainte qui n'a pas bougé, c'est la validation client. « Même si on peut faire une vidéo en une journée, elle doit quand même remonter la chaîne », dit Sheffer, et ce cycle d'approbation fixe le vrai rythme d'un projet, quelle que soit la vitesse de l'étape de génération. Une distinction qui mérite qu'on s'y attarde : la valeur ici n'est pas un délai plus court, mais un plafond bien plus élevé sur ce qui tient dans le délai dont tu disposes déjà.
Le prochain défi de taille
The newest thread Mile 80 is pulling on is live action. Rather than generating a scene from scratch, the team is testing what happens when real footage, shot quickly and simply, gets AI effects, creature work, or set extension added in post. Sheffer thinks there's real room to run here: "I could see a workflow for sure of filming with an iPhone and getting out high quality Hollywood blockbuster style," he says, enough that he half-jokes about the approach eventually undercutting the traditional camera market.
The limiting factor, in his view, is still human emotion. "Our eyes are so used to, and our brains are so used to, knowing that's a human being, that it's always the hardest thing to fake," he says. That's part of why he's also been thinking through quicker face-replacement pipelines, layering real webcam performance onto a generated character rather than trying to generate the performance itself. It's a fitting place for the story to land: even the team most willing to push a pipeline as far as it can go still draws the line at the same place, the parts of the work that come from being human.