Filter

My recent searches
Filter by:
Budget
to
to
to
Type
Skills
Languages
    Job State
    315 comfyui jobs found

    ...robóticos Cabezas parlantes estáticas Apariencia obvia de IA expresiones faciales antinaturales Manos rotas o movimientos corporales El rostro cambia entre tomas. Mala sincronización labial Fondos parpadeantes o inestables HERRAMIENTAS Puede utilizar cualquier flujo de trabajo de IA profesional que considere apropiado, incluyendo: Veo, Kling, Runway, Hailuo, HeyGen, Flux, Midjourney, ElevenLabs, ComfyUI, Stable Diffusion u otras herramientas. No es necesario que utilices una herramienta específica. Lo que nos importa es el resultado final, no el software que uses. POR FAVOR, INCLUYA EN SU PROPUESTA Tu portafolio. Ejemplos de humanos con inteligencia artificial realistas que hablan. Ejemplos de humanos controlados por IA caminando/moviéndose...

    $101 Average bid
    $101 Avg Bid
    18 bids

    ...formatos 4:5, 9:16, 1:1 y horizontal. Retoque final en Photoshop, Canva, Figma, CapCut, Premiere o similar. Variaciones de una misma línea creativa para test A/B. Propuestas visuales alineadas con marca, no piezas sueltas sin coherencia. Herramientas que valoramos No es obligatorio usar todas, pero sí debes dominar varias herramientas de IA visual y edición: Midjourney Stable Diffusion / Flux / ComfyUI Runway Kling Hailuo Veo Photoshop After Effects / Premiere / CapCut Canva o Figma para composición publicitaria Herramientas de voz, avatar o UGC con IA si las usas Estilo visual buscado Buscamos una estética: Hiperrealista. Editorial. Premium. Natural. Elegante. Limpia. Cuidada. Con piel humana real, no plástica. Con composición...

    $127 Average bid
    $127 Avg Bid
    21 bids

    Especialista en IA - Entrenamiento...ángulos. • Manejo avanzado de prompts para texturas complejas (materiales sintéticos y orgánicos) e iluminación cinematográfica. • El modelo debe estar optimizado para estética fotográfica "RAW" y realismo extremo. ENTREGABLES OBLIGATORIOS (Para liberación de pago): 1. Archivo .safetensors del LoRA entrenado. 2. Dataset de imágenes utilizado. 3. Trigger words (prompts de activación). 4. Workflow de ComfyUI o Forge para replicar la calidad. 5. Prueba de consistencia en 5 escenarios diferentes. Nota: Los detalles específicos sobre la temática y el nicho estético se discutirán exclusivamente en privado por chat una vez revisado el po...

    $189 Average bid
    $189 Avg Bid
    25 bids

    Busco apoyo para ampliar ComfyUI añadiendo nuevas funcionalidades centradas en el desarrollo y la optimización de flujos. Mi objetivo principal es: • Integrar módulos que faciliten la creación, edición y mantenimiento de flujos complejos. • Mejorar la eficiencia general de los flujos existentes y simplificar cada paso para que cualquier usuario pueda configurarlos sin pasos redundantes. • Incluir un soporte sólido que permita escalar o adaptar las soluciones en futuras iteraciones. Trabajo normalmente con Python y entornos basados en Stable Diffusion, por lo que agradeceré experiencia previa con estos stacks y con la arquitectura interna de ComfyUI. Necesito código limpio, documentado y con ejemplos ...

    $25 / hr Average bid
    $25 / hr Avg Bid
    29 bids

    Quiero automatizar...es contar con un flujo en ComfyUI que, al recibir esa foto, detecte la prenda, la recorte correctamente y la inserte en una composición flat lay con un fondo limpio y balanceado, replicando el estilo de la referencia que adjunto. El resultado final debe ser un JPG o PNG listo para subirse a mi catálogo de productos, manteniendo la fidelidad de los colores y las texturas originales. Necesito el archivo JSON del workflow de ComfyUI y una breve guía de uso para que pueda reaplicarlo con otras imágenes de la misma prenda sin mayor ajuste. Si durante el proceso se requieren nodos o extensiones específicas, indícalos en la guía para poder instalarlos. Acepto sugerencias de optimización siempre que el fl...

    $146 Average bid
    $146 Avg Bid
    13 bids

    ...y validación en un entorno local (PC del cliente). ________________________________________ Lo que Buscamos Buscamos un experto en Python con experiencia sólida en el desarrollo de soluciones de IA. Idealmente, que tenga conocimientos de todas o la mayoría de las siguientes tecnologías: • Lenguajes: Python (indispensable). • IA/ML: Experiencia con APIs de LLMs (GPT, Llama), Stable Diffusion y ComfyUI. • Librerías Clave: OpenCV, PySceneDetect, MoviePy. • Bases de Datos: MongoDB. • Scripting: Conocimiento en scripts de shell (.bat, .sh) para automatizar instalaciones. • Herramientas: Git y, de forma ideal, experiencia con Docker para la implementación. ________________________________________ Alcance y Hitos de...

    $761 Average bid
    $761 Avg Bid
    35 bids

    ...por personaje (GPT-based) • Generación de imágenes realistas mediante IA (Stable Diffusion, con prompts personalizados por personaje) • Sistema de login seguro (email / OAuth) • Módulo de monetización (suscripciones o sistema de créditos) • Panel de administración básico • Implementación en servidor (puede ser VPS, Render, o similar) Tecnologías preferidas: , Supabase, Node, Python, ComfyUI, RunPod, etc. Somos flexibles si justificas otra stack. Importante: Queremos trabajar con alguien que tenga experiencia en plataformas dirigidas a mayores de edad (contenido sensible o expresivo, sin censura automática). No es necesario mostrar ejemplos explícitos, pero sí demos ...

    $1368 Average bid
    $1368 Avg Bid
    35 bids

    Necesito un experto en ComfyUI para generar imágenes privadas explícitas nsfw estilo anime de alta calidad con buen detalle, debe tener la capacidad de generar personajes consistentes, Ver las referencias, necesito muchas imágenes por lo que pagaré $0.1 por imagen aunque puedes proponer tu precio y vere si es lo suficientemente bueno para considerarlo. Te pediré una imagen de prueba para ver si eres elegible***.

    $70 Average bid
    $70 Avg Bid
    13 bids

    Necesito un experto en ComfyUI para generar imágenes privadas explícitas nsfw estilo anime de alta calidad con buen detalle, debe tener la capacidad de generar personajes consistentes, Ver las referencias, necesito muchas imágenes por lo que pagaré $0.1 por imagen aunque puedes proponer tu precio y vere si es lo suficientemente bueno para considerarlo. Te pediré una imagen de prueba para ver si eres elegible***.

    $18 Average bid
    $18 Avg Bid
    5 bids

    ...and short videos—with a realistic, everyday-life aesthetic. Your role is to craft and refine the prompts that make the most of today’s diffusion and generative video models, control the tone so it remains natural rather than over-stylised, and document exactly how each shot or clip can be reproduced on demand. Feel free to use any tools for Stable Diffusion (A1111 + ControlNet + LoRA support), ComfyUI, and Runway/MagicAnimate for video. If you prefer Midjourney, DALL·E, Pika Labs, or similar platforms for specific shots then feel free to use so. The core of the assignment is simple: supply images and videos that reliably showcase photo-realistic NSFW scenes based on the characteristics that we decide and they should be grounded in everyday scenarios—thi...

    $12 / hr Average bid
    $12 / hr Avg Bid
    26 bids

    ...entirely in Arabic (Saudi/Gulf dialect). You must be able to read the Arabic storyboard effortlessly and ensure proper Arabic typography/RTL formatting in post-production without any broken letters or translation errors. * **Proven Expertise in Higgsfield AI:** Strong, hands-on experience using **Higgsfield** (alongside any supporting AI tools in your workflow such as Midjourney, Runway, Kling, or ComfyUI) to control camera movements, human expressions, and character consistency. * **Mastery of Character Consistency:** You must demonstrate how you keep the exact same face, outfit, and room geometry across different shots and actions without morphing. * **Commercial Editing Skills:** Strong proficiency in After Effects / Premiere Pro for compositing screen inserts, Arabic UI pop...

    $424 Average bid
    $424 Avg Bid
    45 bids

    I’d like a set of ComfyUI-based workflows that let end-users either upload an existing photo or start from a text prompt, then move smoothly into editing or enhancement inside the same pipeline. My goal is to give them the flexibility to replace backgrounds, fix portraits, or generate entirely new marketing visuals—whatever their creative need—without forcing separate tools or extra steps. Here’s what I need from you: • One or more ready-to-run ComfyUI graphs (.json) covering both entry points: “upload & edit” and “prompt-to-image.” • Any custom nodes, checkpoints, or ControlNet/LoRA weights the graphs rely on, packaged or clearly linked. • A concise README that explains setup, required versions (Comf...

    $150 Average bid
    $150 Avg Bid
    64 bids

    ...fonts or plugins required. - A short list of workflow changes and unresolved issues for review. Who we’re looking for - Strong English writing and editing skills. - Experience editing screen-recorded software tutorials. - Hands-on experience with AI image/video tools such as Seedream, Veo, or Wan. - Comfort working with node-based canvas workflows and learning a new platform. - Have knowledge of comfyUI is a big plus. - Good judgment about when to translate, simplify, or re-record. We’ll provide access to MagicCanvas, the original course materials, and brand/style guidance. We’ll start with one paid trial lesson before moving to a larger batch. Please include relevant work samples, your preferred editing software, your availability, and an estimated price and...

    $374 Average bid
    $374 Avg Bid
    44 bids

    ...real (legs and wheels actually cycle — nothing is slid across a background), figures stay grounded on their surface, everything is sized and positioned in true proportion to the scene, and speaking/singing characters are animated so their words can be read on their lips. We will share a short reference clip that defines the standard; every delivery is judged against it. Tools: our pipeline uses ComfyUI/Wan and standard 2D animation tools; experience with either (or both) is welcome. You work on your own machine. Process: NDA first (typed-name signature is fine). Then a short PAID test piece, judged on one thing — whether the motion reads as real. If it passes, the engagement becomes ongoing weekly production. To apply: tell us (1) which tools you work in, (2) a lin...

    $9 / hr Average bid
    $9 / hr Avg Bid
    46 bids

    ...company seeks an experienced ComfyUI / Wan 2.x operator for an ongoing production seat. THE JOB - Produce scripted, choreographed dance-performance features (approx. 6 minutes each) of ORIGINAL FICTIONAL adult characters, from our written scripts: choreography cue sheets, costume-state guides, reference images, and existing workflow/driver material are provided. - Work runs on our established Wan VACE pipeline (reference + control driven). You may build on our pipeline or bring your own, provided output matches the house style and character references exactly. - First engagement is a PAID TEST: one short chunk, judged on one thing — the character's face and identity hold at full-body distance, in motion, with no smearing or drift. REQUIREMENTS - Demonstrated Comfy...

    $121 Average bid
    $121 Avg Bid
    26 bids

    We're looking for an AI prompt engineer experienced in NSFW image generation. You'll build and validate a full production pipeline on our current platform, then deliver a user-facing version our users can run directly. This is a one-time project. Requirements: Proficient in ComfyUI and Krea Experience with SeaArt or similar platforms preferred A portfolio of NSFW AI work Adult (18+) fictional content only. No real people. Tags: ComfyUI · Krea · Stable Diffusion · Prompt Engineering · AI Image Generation · AI Content Creation

    $941 Average bid
    $941 Avg Bid
    54 bids

    ...work—yet created primarily through generative tools rather than a physical crew. Here’s what I need from you: • A full video for each story I provide (or that we co-develop) rendered in HD or higher, delivered as an MP4. • Any project files or prompts you use so I can archive and iterate later. I’m open to whichever combination of platforms you prefer—Runway, Sora-style diffusion models, ComfyUI, Stable Video, Unreal MetaHuman, DaVinci Resolve, or your own custom pipeline—so long as the final look lands squarely in “live-action movie realism.” Sound design and basic grading are a plus but not mandatory; we can discuss that once the visual quality is locked. To help me choose, please share: • A link to at least on...

    $10 / hr Average bid
    $10 / hr Avg Bid
    47 bids

    Title: AI Animator for Adult Anime Game (Wan 2.2 / ComfyUI), Long-term We're a Taiwan-based adult game studio looking for an AI animator to turn our static CGs into seamless 3-5s looping animations (image-to-video). - Spec: 720p+, 24/30fps, MP4 or WebM - Tools: ComfyUI, Wan 2.2, LoRA experience preferred - Volume: paid trial of 2 clips first; more work (50-200 clips/month) if the trial goes well - Quote: price per usable clip, with portfolio samples - Terms: all characters are adults (18+), no real-person likeness; full copyright transfers to us; NDA, no public posting, no subcontracting without consent; deliver workflow files with each batch

    $60 Average bid
    $60 Avg Bid
    44 bids

    ...and now need a steady flow of short, hyper-realistic videos produced entirely with modern AI tools. Each piece will explain a single concept in an engaging, interactive style—think bite-size lessons that feel cinematic rather than slide-deck-boring. The immediate priority is a batch of realistic shorts. You must be fluent with current AI video pipelines (Runway, Pika, HeyGen, Stable Diffusion / ComfyUI, Unreal/MetaHuman, or similar), able to keep characters visually consistent from scene to scene, and comfortable syncing AI-generated or human voice-overs to natural lip movement. Smooth camera moves, proper lighting, and polished color grading are essential; the final result should stand up next to traditional live-action work. Although the focus is on educational shorts, ...

    $365 Average bid
    $365 Avg Bid
    67 bids

    Please ensure to include work samples specific to AIGC and AI Agent creation in your proposal. This will help me streamline the selection process. I am looking for an experienced ComfyUI specialist to build an original, realistic AI influencer from scratch, and set up a complete cloud-based content pipeline that I can run myself. The character will mainly be used for brand-safe UGC, TikTok Shop and affiliate content on TikTok and Instagram. What I need: 1. Character creation and LoRA training - Design an original, photorealistic character (not based on a real person) - Build the training dataset and train a LoRA (Flux or another model you recommend) - The face and body must stay consistent across images and videos 2. Image generation workflow - Text-to-image workflow with the Lo...

    $146 Average bid
    $146 Avg Bid
    91 bids

    ...channel, topic, scheduled time, generation status, rendering status, publishing status, YouTube URL and errors. Failed jobs should be retryable. For automation, I should be able to set schedules such as 3 Shorts per day at specific times. The system should automatically generate and publish content according to the queue. Please prioritize FREE/open-source technologies such as Ollama/local LLMs, ComfyUI, Stable Diffusion/SDXL, Whisper/faster-whisper, Piper TTS, FFmpeg, Python, Laravel and MySQL/SQLite wherever practical. Do not make the application dependent on one expensive AI provider. AI services should be configurable so I can replace them later. The system should be mobile-friendly, secure, modular and easy to manage. Include video preview, manual editing of titles/descr...

    $23 Average bid
    $23 Avg Bid
    66 bids

    # Build a Higgsfield AI Alternative – AI Image & Video Generation Platform (Ollama, OpenRouter, Multi-API Integration) **Project Type:** Full-Stack Development / Artificial Intelligence / Generative AI **Skills Required:** Python, React.js, , Node.js, FastAPI, Generative AI, Ollama, ComfyUI, Stable Diffusion, API Integration, AI Video Generation ## Project Overview I am looking for an experienced AI developer or development team to build a fully functional, self-hosted AI image and video generation platform inspired by **Higgsfield AI ()**. The goal is to develop a powerful, modern, user-friendly platform that provides similar creative capabilities to Higgsfield while allowing me to use **local AI models, free APIs, paid APIs, and third-party AI providers**

    $6942 Average bid
    $6942 Avg Bid
    187 bids

    ...AI-generated adult characters. The project 3-5 minute short with a story-driven, stylish, adults-only tone Fictional characters only, all clearly adult, no real people's likenesses Cinematic look: consistent characters, strong lighting, professional sound and color You are A proven AI filmmaker or creative director with finished narrative work in your portfolio Skilled in self-hosted pipelines (ComfyUI, Stable Diffusion/Wan, custom LoRAs), since most mainstream tools (Veo, Runway, Sora, Kling) prohibit sexual content Strong in editing, compositing, color grading, and sound design Experienced with character consistency across shots Production workflow Script and storyboard Design original adult characters (trained on your own synthetic or licensed data) Generate shots w...

    $27 / hr Average bid
    $27 / hr Avg Bid
    13 bids

    I need an engineer who can look at my current ComfyUI setup and turn it into a smoother, faster-moving pipeline. My top priority is streamlining every stage of the workflow, and that means tackling three fronts at once: task automation, richer data visualization, and a cleaner, more intuitive user interface. Right now ComfyUI is already in place, but several internal tools feed data into it. Those integrations work, yet they feel bolted-on and create extra clicks and manual steps. Your job is to tighten those connections, automate what I still do by hand, and surface clear metrics so I can see bottlenecks at a glance. Key deliverables • End-to-end workflow map showing the revised pipeline and where each automation kicks in • Modular scripts or nodes that handl...

    $34 / hr Average bid
    $34 / hr Avg Bid
    106 bids

    ...production pipeline to run locally. The plan is to rely on ComfyUI as the core “orchestrator” and generate hyper-realistic clips in which character animation, scenery setup, and voice synchronisation happen automatically from a short prompt or script. You will need to select, install, and optimise the best local models (image-to-video or 3D motion, TTS, lip-sync, etc.) so they run smoothly on the 5090’s VRAM without calling external APIs. Once the models are in place, I expect a ComfyUI graph—or an equally efficient node-based setup—that ingests a text prompt, produces the visuals, aligns the audio, and renders a finished clip. Deliverables • Fully configured local environment with all required models and dependencies • A rea...

    $451 Average bid
    $451 Avg Bid
    78 bids

    ...face - The same hairstyle - The same approximate body type - The same age appearance - The same skin tone and physical characteristics - The same overall aesthetic and personality The character cannot look like a slightly different person every time a new image or video is generated. Experience with LoRAs, character models, reference-image workflows, face consistency, ControlNet, IP-Adapter, ComfyUI, Stable Diffusion, Flux, or similar tools would be very valuable. Content References There is a huge amount of existing social-media content that can be used as creative and stylistic reference for poses, camera angles, settings, video concepts, outfits, trends, and compositions. I am looking for someone who can efficiently study successful creator content and produce original va...

    $174 Average bid
    $174 Avg Bid
    114 bids

    ...please include: Your experience with protected sites (DataDome, Cloudflare or similar). Examples welcome. The technology and approach you'd use for Allegro. Monthly running costs at 5k, 20k and 50k products. Whether maintenance after changes on Allegro's side is included, and at what rate. Ogłoszenie 2 Title: Local AI pipeline (ComfyUI) – furniture packshots & interior shots from product photos, batch, colour-accurate Description: I need an experienced ComfyUI / Stable Diffusion / Flux specialist to build a local, batch image-generation pipeline for upholstered furniture (sofas, sofa beds, corner sofas) for a UK furniture seller. Important: no paid AI APIs (Google, OpenAI, Grok etc.). The whole pipeline must run on self-hosted open models on my own...

    $502 Average bid
    $502 Avg Bid
    158 bids

    ...across various lifestyles, wardrobes, and environmental aesthetics. Utilize custom LoRAs, Textual Inversion, and ControlNet to maintain facial and body proportions across different poses and scenes. Organise weekly content drops, including teaser assets for social media and premium assets for our paywalled subscription feeds. Requirements: Advanced proficiency in Stable Diffusion (Automatic1111, ComfyUI, Forge, or Draw Things). Mastery of ControlNet (OpenPose, Depth, IP-Adapter) to direct character poses and compositions. Proven experience in training custom LoRAs or Embeddings for character consistency. Project Scope: This project operates within highly-regulated creative boundaries for a mature-audience demographic. Visual themes include high-end aesthetic modeling, lingerie, a...

    $504 Average bid
    $504 Avg Bid
    26 bids

    ...promotional content only. All reference images will be supplied with permission from the individuals involved. The project does not involve impersonation, deceptive content, unauthorized use of a person's likeness, or misleading representations. 4. Preferred Experience We would like to work with someone who has experience with: * AI image-to-video generation * Realistic human video generation * ComfyUI workflows * Kling, Runway, Veo, Hailuo, or similar platforms * FLUX / Stable Diffusion or related image-generation tools * Character consistency * AI artifact reduction * Short-form social media video production * Workflow automation or reusable generation pipelines You do not need experience with every tool listed above. Quality, realism, and a reliable workflow are mo...

    $362 Average bid
    $362 Avg Bid
    115 bids

    ...Avataren, szenischen Bewegungen und perfekt passenden Lippenbewegungen zur TTS-Sprachausgabe. Was mir dabei am wichtigsten ist: • Audio-to-Video Lipsync hat höchste Priorität; die Lippen müssen exakt zum generierten Audio passen. • Der Workflow soll in ComfyUI orchestriert werden, da ich dort bereits Modelle und Nodes verwalte. • Absolute Charakter-Konsistenz über alle Clips hinweg ist Pflicht; Stil-Drift darf nicht vorkommen. Kernaufgaben für dich: 1. Entwerfen und implementieren eines End-to-End-Workflows in ComfyUI, der – Text-to-Video oder Image-to-Video Animationen für einfache Szenen startet, – mithilfe von Stable Diffusion, Wan, Kling, LivePortrait (oder gleichwertigen Tools) die Be...

    $36 / hr Average bid
    Local
    $36 / hr Avg Bid
    7 bids

    ...proprietary commercial models (e.g., Anthropic Claude, OpenAI GPT-4o) or open-source foundation models (e.g., LLaMA 3, Mistral) served via high-performance inference engines like vLLM. * **Vector Database:** Pinecone, ChromaDB, or pgvector (PostgreSQL) specialized in semantic context retrieval and user memory retention. * **Multimedia Pipelines:** Stable Diffusion (via Replicate, Ideogram, or ComfyUI instances) for imagery, and ElevenLabs or equivalent text-to-speech engine for high-fidelity voice output. * **Database & Cache:** PostgreSQL for transaction and user tables; Redis for fast session management and prompt-response caching. ### 4. Developer Requirements & Qualifications ### Technical Competencies * Proven experience building **production-grade Generative AI a...

    $627 Average bid
    $627 Avg Bid
    295 bids

    我正在用 ComfyUI 打造一套「数字人探校」短视频系列,覆盖美国 US 前 30、英国 QS 前 200、香港前 8、新加坡前 5、澳洲八大、新西兰前 3 和加拿大前 5 的大学。现在缺少完整工作流与校园数字资产,想在 3 天内拿到一个可直接投产的解决方案。 我需要你交付: 1. 一套可导入 ComfyUI 的工作流文件,让我只需输入学校主题或关键词,就能自动生成脚本、分镜、配音台词及场景列表。 2. 可复用的校园 3D/2.5D 模型或高质量图像资产,能匹配上述高校的代表性建筑与氛围。 3. 自动将脚本-分镜与校园模型绑定,输出适配抖音和小红书的成片(9∶16,1080 × 1920)。 4. 简明操作文档与演示视频,确保流程可一键复现。 重点:脚本内容、分镜设计、校园建模三者同样重要。 请在申请里提供详细的项目建议,说明你将如何: • 获取或生成各校模型与素材 • 在 ComfyUI 中实现脚本-镜头-模型的关联逻辑 • 保证 3 天内交付可运行版本,并列出后续可扩展方向 期待与你合作。

    $210 Average bid
    $210 Avg Bid
    7 bids

    ...AI video generation * Lip-sync / voice synchronization * Different environments, outfits and scenes while maintaining character consistency * Reels/Shorts and potentially longer-form videos * Final videos without watermarks * Good understanding of current AI video-generation tools/workflows Tools can be anything you’re comfortable with — **HeyGen, Kling, Runway, Veo, Hailuo, Hedra, Seedance, ComfyUI, or other workflows**. I’m more interested in the **quality of your output** than the specific tool you use. Please send me: 1. **2–5 best samples** of your AI-generated human/female character videos 2. Examples showing **the same character/face maintained across multiple videos**, if available 3. Which AI tools/models you use 4. Your workflow — how yo...

    $11 / hr Average bid
    $11 / hr Avg Bid
    26 bids

    We’re looking for an experienced AI video producer to create longer-form NSFW AI videos using tools such as ComfyUI, Wan, LTX Video, Hunyuan or similar workflows. The goal is to produce coherent 5–10 minute videos by combining shorter generated clips while maintaining strong consistency in the character, environment, clothing, camera style and overall look. You should have experience with areas such as: * ComfyUI * Wan / LTX / Hunyuan * Image-to-video * Character consistency * LoRAs / reference conditioning * Frame continuation * Upscaling / interpolation * Video editing and post-production This is ongoing paid work, not a one-off project. We are specifically looking for someone who understands the technical side of AI video generation, rather than only using...

    $120 Average bid
    $120 Avg Bid
    70 bids

    Role Generative AI Pipeline Technical – ComfyUI + Nuke Experience: 4–6 years of relevant experience, including strong VFX/compositing experience and extensive hands-on work with ComfyUI-based Generative AI pipelines. About the Role It is an AI-Native Content Studio building production pipelines for advertising, e-commerce, social media, animation, short films, filmmaking, micro-dramas and OTT-led content. We are looking for someone who can architect, build and own advanced end-to-end Generative AI workflows in ComfyUI, particularly for video-led content production. This is not a ComfyUI operator role. The person should have independently built sophisticated production workflows from scratch and should be comfortable working at the intersection ...

    $2190 Average bid
    $2190 Avg Bid
    8 bids

    -Creating a persistent ComfyUI environment in RunPod Network Volume with all the versions of all available pip packages and git repos being locked. -Creating a custom script to auto-terminate the Pod on idle -Explainer video, documentation, backups and such. $350 fixed, in two payments: $175 when both workflows load on the Network Volume with zero missing nodes, $175 after test runs, guide, recording and backup archive are delivered

    $350 Average bid
    $350 Avg Bid
    1 bids

    I’m ready to master ComfyUI (or any comparable AI workflow you suggest) so I can take the viral TikTok clips I already picked out and replace the main face with a chosen celebrity—complete with fluid, believable body-tracked motion and a matching voice-over. What I need from you is a practical, step-by-step learning experience. Screen-shared sessions, clearly annotated workflow files, and demo renders will help me understand every stage: prepping the source video, refining masks, driving facial expressions from audio, and blending everything back into the original clip without obvious artefacts. Realistic motion is my top priority, so please be ready to dive deep into motion tracking, lip-sync alignment, and frame-by-frame polish; I’m happy for you to point me t...

    $10 / hr Average bid
    $10 / hr Avg Bid
    15 bids

    ...built in ComfyUI that pulls directly from that LoRA or from the reference photos I provide so the on-screen “AI girl” is a perfect match. Visually, I’m picturing a blend of sweeping cityscape shots and calmer nature interludes, stitched together so the mood follows the flow of the song. Dynamic lighting should drive key transitions, with tasteful particle effects and occasional slow-motion moments to accent beats or lyrical cues. All animation, compositing and colour work has to look natural rather than stylised or cartoonish. You’ll receive: • the mastered audio file • the LoRA model / photo set for the character reference • any extra style notes or timestamps that highlight musical peaks I’d like the final piece delivered as a...

    $144 Average bid
    $144 Avg Bid
    77 bids

    ...GPU time and estimated cost for each production so I know actual cost for 30/60/90/120-second productions. API: Create a versioned ROLLCALL API including GET /v1/health, GET /v1/certify, POST /v1/jobs, GET /v1/jobs/{id}, POST /v1/jobs/{id}/cancel, GET /v1/workers, GET /v1/models and POST /v1/worker/heartbeat. Website communicates with the ROLLCALL API, not directly with random Python scripts/ComfyUI workflows. Secure GPU endpoints using server-side API keys/service authentication. Never expose GPU/API secrets in browser code. STORAGE + DATABASE: Use S3-compatible storage such as S3/R2/B2 for large video/image/audio assets. Database entities should include Users, Projects, Productions, Scenes, Shots, Segments, Characters, CharacterReferences, Locations, Storyboards, Assets, Rend...

    $1038 Average bid
    $1038 Avg Bid
    196 bids

    ...GPU time and estimated cost for each production so I know actual cost for 30/60/90/120-second productions. API: Create a versioned ROLLCALL API including GET /v1/health, GET /v1/certify, POST /v1/jobs, GET /v1/jobs/{id}, POST /v1/jobs/{id}/cancel, GET /v1/workers, GET /v1/models and POST /v1/worker/heartbeat. Website communicates with the ROLLCALL API, not directly with random Python scripts/ComfyUI workflows. Secure GPU endpoints using server-side API keys/service authentication. Never expose GPU/API secrets in browser code. STORAGE + DATABASE: Use S3-compatible storage such as S3/R2/B2 for large video/image/audio assets. Database entities should include Users, Projects, Productions, Scenes, Shots, Segments, Characters, CharacterReferences, Locations, Storyboards, Assets, Rend...

    $1257 Average bid
    $1257 Avg Bid
    243 bids

    ...rather than generic stock footage. Nebulas swirling to the beat, particles forming sacred geometry, stardust pulsing in sync with a mantra—anything that instantly signals “transcendence” while remaining tasteful and calming. I’m not looking for cookie-cutter templates; the visuals should feel generated specifically for each snippet. No restriction on whether you use Runway Gen-2, Stable Diffusion/ComfyUI with Deforum, or a custom pipeline of your choice. Post-work in After Effects, Premiere, or DaVinci is fine as long as the final result is 9:16, 1080 × 1920, ready to post, and under 60 MB. Light background music will be needed. Captions will be provided (in the form of transcripts) and will be needed in the videos. Deliverables (per clip): • ...

    $209 Average bid
    $209 Avg Bid
    7 bids

    ...photography** with visible pores, natural skin texture, tonal variation, realistic folds/compression, subtle asymmetry, believable anatomy, and natural fabric/skin interaction. **NO plastic AI skin, excessive smoothing, CGI appearance, or obvious AI anatomy.** ### Technical Experience I’m open to the best workflow for achieving this. Relevant experience may include: **FLUX, Stable Diffusion/SDXL, ComfyUI, LoRA training, ControlNet/OpenPose, IP-Adapter, PuLID/InstantID, multi-reference conditioning, custom character models, or comparable AI character-consistency tools.** Experience with **Higgsfield/SOUL and AI video generation is a major plus.** The finished body references will be provided to me for use in Higgsfield SOUL and other image/video generators. You will **n...

    $123 Average bid
    $123 Avg Bid
    42 bids

    ...of ComfyUI, Open WebUI, and n8n. AI Character & Video Production Pipeline: Build advanced ComfyUI workflows leveraging SOTA open-source video/image models. Implement character consistency tools using LoRAs and IP-Adapter/ControlNet pipelines. Integrate lip-sync and dialogue tools (e.g., LivePortrait, MuseTalk, ElevenLabs, or equivalent). Apply cinematic director tools (camera movement control, upscaling, frame interpolation). Automation & Multi-Platform Distribution: Create n8n automated workflows connecting rendering, video assembly, audio mixing, and export. Auto-posting pipeline for social media channels (Facebook, Instagram Reels, TikTok). Separate workflow path for rendering and managing NSFW versions for paid platforms. Required Skills & Technical Stack ...

    $1209 Average bid
    $1209 Avg Bid
    80 bids

    **PLEASE READ BEFORE APPLYING** I am looking for an **ADVANCED COMFYUI EXPERT**, specifically for building and teaching **complex AI video workflows**. This is **NOT** a general AI video job. If your main experience is with Kling, Runway, Higgsfield, Midjourney, Leonardo, etc. but you do not build advanced workflows directly in **ComfyUI**, please do not apply. ### I need someone experienced in: * Advanced ComfyUI workflow architecture * Current image + video models inside ComfyUI * Image-to-video / video-to-video * Character consistency and identity preservation * LoRA training and implementation * ControlNet / conditioning / reference systems * Temporal consistency * Character + environment integration * Real location + AI character * AI environment + con...

    $95 Average bid
    $95 Avg Bid
    10 bids

    # ComfyUI AI Video Expert / Mentor – Professional Cinematic Workflows I am looking for an **advanced ComfyUI + AI Video professional** to teach me how to build professional, photorealistic video workflows for commercial production. I am **not looking for ready-made workflows**. I want to learn how to build, understand, modify and troubleshoot them myself. ### What I want to learn * Real location + AI characters + real clothing/products * AI environments + consistent realistic characters * Fully AI-generated cinematic scenes * Dialogue, lip-sync and realistic acting * Music videos * Character consistency across shots and episodes * Camera, lighting, motion and cinematic realism * Image-to-video / video-to-video pipelines * LoRA and character identity systems * Tempor...

    $182 Average bid
    $182 Avg Bid
    28 bids

    ...important requirement is CHARACTER CONSISTENCY. The character must remain recognizable when used in different scenes, camera angles, poses, locations, lighting conditions and clothing. The first scene I provided in the screenplay will be used as the initial visual reference for the character. I am open to your preferred professional AI workflow, including Midjourney, Flux, Stable Diffusion, ComfyUI, DALL-E or other tools. Please let me know: 1. Your fee for this pilot character development 2. What exactly is included in the pilot package 3. Estimated turnaround time 4. Which AI tools/workflow you would use 5. Examples of previous cinematic AI character work 6. Whether commercial usage rights are included If the pilot character meets our expectations, we would then move forw...

    $89 Average bid
    $89 Avg Bid
    88 bids

    Project title 3D-AI Animator for NFC Product Video (hand-tap interaction, hyperrealistic) Description I'm looking for a specialist experienced in AI-assisted generative animation (ComfyUI, Stable Diffusion/FLUX + ControlNet, IP-Adapter, or an equivalent pipeline) to produce 3 short video sequences showing a person tapping a smartphone on physical NFC products (keychains, counter plates, wall plates). I have 3D model files (.GLB) of the products and reference renders to guarantee brand fidelity. The focus of this project is achieving photorealism in the hand-object-phone interaction, without altering the design, logo, or geometry of the real product. Non-negotiable technical requirements Product fidelity: the product in the final video must be identical to the provided GLB/sa...

    $122 Average bid
    $122 Avg Bid
    61 bids

    ...yet indistinguishable from a live-action shoot. The final spot must look photorealistic, run 20–30 seconds, and be delivered in 4K (16:9) ProRes along with the project files so I can make future tweaks if needed. Here is what I expect: • A clear treatment that explains the concept, visual approach, and any AI models you plan to combine (e.g., Stable Video Diffusion, Runway Gen-2, Midjourney, ComfyUI, or your own fine-tuned model). • Scene-by-scene generation, clean compositing, and color work so lighting, shadows, and motion match real-world physics. • Professional sound design and a simple music bed with full usage rights. • One round of revisions for timing, color, or minor content adjustments. Please include links to past photorealistic AI...

    $28 Average bid
    $28 Avg Bid
    65 bids

    ...other important details changing between AI-generated scenes. ## Who We Are Looking For We prefer freelancers with experience creating: * AI-generated product commercials * Consumer electronics / home appliance advertisements * Cinematic product videos * Photorealistic AI video * High-quality branded advertising content Experience with tools such as **Kling, Veo, Runway, Midjourney, Flux, ComfyUI or similar AI production tools** would be an advantage. ## When Submitting Your Bid Please include: 1. Examples of your best **AI-generated product commercials** 2. Which AI/video tools you use 3. How you would ensure our product remains visually accurate throughout the video 4. Whether **scriptwriting, storyboard and voice-over** are included 5. Number of revisions included 6. Yo...

    $376 Average bid
    $376 Avg Bid
    97 bids

    I’m ready to level-up my production stack with a rock-solid LTX 2.3 + ComfyUI pipeline that keeps both the face and the voice perfectly locked from the first frame to the last. The end goal is a reusable workflow I can drop into: • UGC-style ads that feel authentic yet never drift • Short narrative pieces • Full-length films My priority is absolute character and audio consistency—no jitter, morphing, or timbre shifts even in multi-minute takes. Platform-wise, I want the solution to stay flexible enough to deploy on web, mobile, and desktop front-ends as the projects demand. Key expectations 1. A repeatable LTX 2.3 / ComfyUI graph (or set of graphs) that handles face-locking, lip-sync, and stable voice generation in a single pass. 2. An ...

    $83 Average bid
    $83 Avg Bid
    7 bids