Comfyui jobs
...home décor products. Generate high-quality lifestyle images and product mockups for eCommerce listings. Create short AI promotional videos for product marketing. Develop new product concepts based on current market trends. Ensure all designs are unique, commercial-ready, and suitable for online marketplaces. Requirements Experience with AI tools such as Midjourney, Flux, Adobe Firefly, ChatGPT, ComfyUI, Runway, Kling AI, or similar. Strong understanding of textile design, patterns, colors, and home décor styling. Knowledge of eCommerce marketplaces such as Etsy, Amazon, Shopify, or Walmart is an advantage. Basic Photoshop or Illustrator skills are a plus. Ability to work independently and deliver projects on time. Salary & Benefits Monthly Salary: ₹15,000–...
...open-source and commercial AI providers through a provider-independent architecture. --- # Technology Stack Backend * Python * FastAPI * PostgreSQL * Redis * Celery Frontend * * MakerKit Lite * Tailwind CSS Infrastructure * Docker * Docker Compose * Linux * GPU Workers Authentication * Self-hosted Supabase * JWT * RBAC AI Providers * AudioCraft * Amphion * OpenVoice * RVC * ComfyUI * Future AI Providers --- Core Responsibilities: Design and implement a Modular AI Gateway (FastAPI) using an Adapter Pattern. Setup and manage GPU Worker Architecture (using RunPod or similar GPU providers). Implement an Orchestration Layer (Celery/Redis) for asynchronous job processing. Build a scalable backend capable of handling Multi-tenancy and Enterprise SDKs. Ensure clean architec...
...generation or AI-assisted scenes where needed * Cinematic transitions and visual continuity * Color grading * Sound design * Licensed music recommendation or selection * On-screen text treatment, if needed * Final delivery in high-resolution format * A repeatable production approach for future videos You may use tools such as Premiere Pro, DaVinci Resolve, After Effects, Runway, Kling, Luma, Pika, ComfyUI, Midjourney, Topaz, Nuke, or equivalent professional tools. We care about the final quality, not the specific software. ## Required Capabilities You must be able to show clear evidence of high-end work in at least one of the following categories: * Luxury real estate video * Luxury resort or hospitality film * Cinematic travel / destination film * Investor or institutional r...
We are building our project AI-native Music SaaS Platform. The platform allows users to generate high-quality songs using AI, including lyrics generation, music composition, audio processing, and future AI video generation. Our architecture is based on + FastAPI + Supabase + Open Source AI Models (AudioCraft, ACE-Step, ComfyUI, Qwen)**. We are not building AI models from scratch—we integrate and customize leading open-source AI projects using our own AI Gateway, SDK, and orchestration layer. Our goal is to build a scalable, enterprise-grade AI platform where users can create music, developers can extend the platform through plugins, and businesses can integrate via APIs. At the moment, we are looking for experienced developers to help build different modules of the platf...
...exercise movement recreated using the AI fitness model, with the exercise name "DB BICEPS HAMMER CURL (STANDING)" displayed on the GIF. Technical Requirements: Video-to-Video AI Generation Motion Transfer Consistent AI Character Generation GIF Processing & Optimization Batch Processing Capability Text Overlay Automation for Exercise Names Preferred Tools: Runway Kling AI Hunyuan Video HyperHuman ComfyUI Stable Video Diffusion Any suitable professional AI workflow When Applying Please provide: Similar AI video or motion transfer projects Portfolio samples Proposed workflow Timeline for processing 1,200 GIFs Cost estimate (per GIF and total project cost) We are seeking a long-term partner who can help us build a uniform AI-powered workout content library for our ...
Job Title: Senior ComfyUI Architect: 8K Lifestyle Photography Character & Garment Swap (High-Interaction Locations) Project Overview: We need an enterprise-grade ComfyUI pipeline to swap characters and garments in high-end, real-world lifestyle photography shots. The Context: Multi-character situational photography in varied real-world locations (e.g., a couple interacting at a restaurant table, a couple relaxing in a spa, a couple Nordic walking, walking through a sunlit park, or interacting in a hotel lobby). The Absolute Constraint: The pipeline must not generate new poses, expressions, or background interactions using text prompts. It must dynamically extract the exact skeletal positions, finger/hand placements, physical body overlaps, and subtle facial micro-expre...
...with a: * Premium look * Luxury branding * Modern pharmaceutical / scientific aesthetic * Clean and minimal design * High-end product visualization * Professional lighting * Realistic materials * Strong e-commerce appeal --- ## AI Tools Are Welcome You're free to use any workflow you prefer. Whether you work with: * Photoshop * Illustrator * ChatGPT Image Generation * Midjourney * FLUX * ComfyUI * Stable Diffusion * Firefly * Any other AI tool ...doesn't matter. **We care about the final quality—not how it's created.** --- ## Image Specifications * Resolution: **1254 × 1254 px** * High-quality output suitable for premium e-commerce websites --- ## Workload Each new website typically requires: **15–20 product images** We launch new ...
...Image-generation model fine-tuning * Video-generation workflows * Character LoRA / style LoRA / product LoRA / motion LoRA * Dataset preparation for image and video training * Captioning, trigger words, overfitting, underfitting, and model quality testing * Python and machine learning * GPU-based model training Preferred Tools / Tech Knowledge Experience with any of the following is preferred: * ComfyUI * Kohya training workflows * Diffusion-based image/video models * Image-to-video pipelines * Video-to-video pipelines * Pose-guided generation * Face-consistency workflows * Reference-based generation * Python * PyTorch * Docker * Git * Cloud GPU setup Important This is not a prompt-writing job. This is not a traditional dashboard/data analytics job. I need someone who has ...
... • Batch ops (parallel, queue, worker) • AI content (caption, copywriting, AIDA, PAS) • Calendar strategy + social media posting • Competitor analysis + trend research Self-improvement (x-cluster): • x5 — Agentic Eval & Self-Critique • x6 — Systematic Debugging (4-fase RCA + auto-loop) • x7 — Problem Shaping (tujuan kabur → subtask presisi) Optional modules (v4.1): • m18 — ComfyUI, Manim, Excalidraw, design system • m19 — macOS control (background-first, no cursor steal) • m20 — Humanizer (AI-tell detector + brand voice) • m21 — Enterprise/defensive (KQL, Mini-HIDS, firewall) ━━━━━━━━━━━━━━━━━━━━ SAFETY MACHINERY ━━━━━━━━━━━━━━━━━━━━ ✓ Spend Gove...
I am assembling a complete series of screen-recorded classes that teach ComfyUI for anime-style image work, starting from absolute basics and moving into expert workflows. The audience should finish each lesson able to reproduce what they just saw, so every video must be a step-by-step walkthrough with voice-over explanations, on-screen shortcuts, and at least one practical exercise. Scope to cover • User-interface navigation and optimal layout set-up • Core nodes, key features, and tool combinations that matter most to anime creation • Realistic-to-anime and anime-to-realistic conversion pipelines, explaining prompt crafting, model selection, and batch processing • Effective use of manga and anime LoRA, including how to import, tweak strength, chain m...
I already have a local install of ComfyUI running on my machine but I need a complete workflow that can take a single NSFW prompt (or a short sequence of stills) and turn it into a smooth 1080p video for my personal website. The end result must look realistic rather than stylised, so please choose or fine-tune a model that keeps skin tones natural, lighting believable, and movement free of the usual artefacts. GPU on my side is super 1660, so optimise accordingly or tell me what to tweak. As long as the pipeline stays inside ComfyUI I’m happy, but if you rely on third-party tools (e.g. Deforum, RIFE, FFmpeg) list those and show how they slot into the graph.
I’m building a short showcase of lively, cartoon-style fantasy worlds and need several AI-driven scene animations to bring them to life. The focus is strictly on environment work—no character rigs or motion graphics—so think floating islands, glowing forests, or whimsical castles rendered in a playful palette. I’d like you to use the AI workflow you know best (Runway, Stable Diffusion, ComfyUI, Blender add-ons—whatever gives a crisp, smooth result) to generate fully animated clips. Each scene should run 15-30 seconds, loop cleanly, and arrive in 1080p MP4 along with any project files so adjustments remain possible later. Deliverables • 3 unique cartoonish fantasy scene loops (15-30 s each, 1080p MP4) • Source assets or project files for ...
I'm seeking a bilingual, China-based expert in AI micro-drama production. Your role will involve: - Advising on choosing the right studios - Setting up technical workflows (Kling, Seedance, ComfyUI) - Project management - Making industry introductions Ideal skills and experience: - Strong industry connections in China - Bilingual proficiency in Chinese and English - Experience in project management and technical setups Your expertise will be invaluable in guiding me through this process.
... The role involves generating AI visuals, creating consistent characters and scenes, editing footage, adding sound design, motion graphics, and delivering polished final videos. Projects may include company profile films, startup stories, product explainers, brand campaigns, and social media content. Requirements: • Experience with AI video tools such as Kling, Veo, Runway, Midjourney, Flux, ComfyUI, or similar platforms • Strong video editing skills using Premiere Pro, After Effects, DaVinci Resolve, or equivalent software • Good understanding of storytelling, pacing, and cinematic visuals • Ability to work independently and meet deadlines Please apply only if you have prior experience creating AI-generated videos. When applying, share: • Your portfol...
I'm looking for a ComfyUI expert to build 2 custom workflows for my AI video production pipeline on RunPod. Workflow 1 — LoRA Training - Set up a working LoRA training workflow (Kohya or FluxGym) - Based on Flux model - I will provide 20-50 training images of my character - Output: trained LoRA file ready to use in ComfyUI Workflow 2 — WAN 2.2 Video Generation - WAN 2.2 I2V or T2V workflow in ComfyUI - Format: 9:16 (480x832), 8 seconds - LoRA slot integrated so my character stays consistent - Upscaler included - Must be simple enough for a VA to operate: just change the prompt and hit Run Please only apply if you have real hands-on experience with ComfyUI, LoRA training, and WAN 2.2.
Project Overview This project focuses on the research, development, ...generated assets seamlessly integrate into mainstream real-time engines like Unreal Engine 5 (UE5) and Unity. Scalability: Build a high-throughput asset pipeline capable of generating thousands of high-quality background props and environment assets for large-scale virtual worlds. Technical Stack & Tools AI & Generative Models: Stable Fast 3D, Tripo3D, Meshy, LGM (Large Multi-View Gaussian Model), ComfyUI (for image pre-processing). Traditional 3D Software: Blender, Autodesk Maya (for post-editing, decimation, and formatting). Texturing & Baking: Adobe Substance 3D Painter (for texture refinement), Delighting algorithms. Target Platforms: Unreal Engine 5, Unity, WebGL / Three.js. File Formats: ....
...animation, but my funds are limited, so clever use of AI-driven techniques is essential. The script is ready and runs roughly three minutes; I can share it the moment we start. What I need from you is a colourful, playful visual treatment that captures kids’ attention and keeps the narrative clear. I’m open to whichever pipeline you prefer—whether that’s an AI frame-generator such as Stable Diffusion/ComfyUI, character rigging in Blender, or a hybrid 2D pass in After Effects—to keep production time (and therefore cost) down while still looking polished. Deliverables • Storyboard or animatic for quick approval • Full-resolution final video (1080p minimum, MP4) with music and basic sound effects • Source files or project files so...
Title: AI Video Tool to Previsualize a Broadway Musical Screenplay (LTX-Video) I'm building a reusable software tool that turns scenes from a musical screenplay into AI-gene...conditioning) • A per-scene edit menu — regenerate, adjust tone/lighting/pacing, change staging or camera, swap or lengthen/shorten beats — so I can iterate on the script • A music/ambience audio layer (I understand synced sung dialogue is a current LTX limitation; open to your approach) • A simple UI I can run myself, with source code and setup docs You should have: hands-on LTX-Video / LTXV experience, ComfyUI, Python, video stitching (ffmpeg), and ideally hosted inference (fal or similar) plus GPU/VRAM handling. Theater or film previz experience is a plus. Please share releva...
I am looking for a talented and professional AI artist specialized in creating high-quality NSFW images using ComfyUI. Looking for detailed, visually striking, and aesthetically pleasing NSFW content that includes characters, scenes, and series — according to specific briefs.. For our current project, we need approximately 150 NSFW images and 10 NSFW videos.
I am looking for a talented and professional AI artist specialized in creating high-quality NSFW images using ComfyUI. Looking for detailed, visually striking, and aesthetically pleasing NSFW content that includes characters, scenes, and series — according to specific briefs. This is a long-term collaboration opportunity. For our current project, we need approximately 150 NSFW images and 10 NSFW videos.
I need a reusable ComfyUI workflow that can take a single still image of my virtual influencer and generate a short, smooth video clip suitable for social posts. The end result should feel entertaining while remaining firmly focused on personal-development themes delivered in a serious, trustworthy tone. Here is what I’m after: • A node-based ComfyUI flow (exported as the .json) that handles image conditioning, motion generation and frame interpolation so the character stays on-model throughout the sequence. • Clear parameter notes for any Stable Diffusion / ControlNet checkpoints, scheduler settings, and the exact nodes you rely on, so I can swap models later without breaking the chain. • File-naming logic that automatically outputs a 1080p MP4 alo...
I need a custom workflow inside ComfyUI that lets me run my existing AI model and work exclusively with images of an adult (NSFW) nature. The goal is to load the checkpoint, pass prompts, view results instantly, and tweak generation parameters without ever leaving the ComfyUI canvas. Here is what I expect: • A clean .json workflow file I can import directly into ComfyUI. • All nodes pre-wired for model loading, sampler, prompt/negative prompt, seed control and upscaling so I can hit “Queue Prompt” and see the final image. • Clear inline labels or notes so I understand where to drop new checkpoints, LoRA files or embeddings in the future. Please deliver the finished workflow, plus a brief text file explaining any folder paths or ex...
...looking for a highly creative AI video producer who specializes in generating cinematic NSFW 2-3 minute videos for virtual characters. This is not a simple prompting job. We need someone with strong taste, real hands-on AI video experience, and the ability to create videos that feel polished, attractive, emotionally engaging, and watchable. You should be comfortable working with tools such as ComfyUI, Wan2.1 / Wan2.2, LTX Video, image-to-video workflows, reference-based generation, character consistency, upscaling, inpainting, frame interpolation, and post-processing. The ideal person is someone who genuinely loves experimenting with AI video, understands what makes content visually appealing, and can turn a character image or concept into a high-quality short scene. We are esp...
...for advertising (5–30 seconds) Create consistent visual style across shots (brand/film look) Improve prompt/design iterations fast (story beats, camera language, pacing) Deliver in multiple formats when needed (16:9 / 9:16 / 1:1) Optional: basic edit/assembly (timing, music placeholders, simple captions) Tools (examples, use what you master): Runway, Luma, Pika, Kling, Midjourney/SD for frames, ComfyUI pipelines, After Effects/Premiere/Resolve for assembly. What we’re looking for: Strong cinematic taste (lighting, lenses, composition, movement) Ability to keep characters/wardrobe/style consistent across shots Clear communication + reliable turnaround A portfolio showing AI-generated video work (ads, trailers, cinematic tests) To apply, please send: Portfolio link...
...exact moment an account hits the platform’s monetization threshold, the software must trigger an automation sequence to launch a brand new set of accounts/channels under the same system architecture to continuously multiply revenue streams. ### **Preferred Tech Stack (Open to Suggestions):** * **Backend/Automation:** Python, Node.js, Celery (for heavy queue management). * **AI/Avatar/Voice:** ComfyUI, SadTalker, HeyGen API, ElevenLabs API, Wav2Lip, or custom PyTorch/TensorFlow pipelines. * **Browser Automation:** Playwright, Puppeteer Stealth, AdsPower/Multilogin API. * **Cloud Infrastructure:** AWS, GCP, or RunPod/ (optimized for cost-effective mass GPU rendering). ### **Deliverables:** 1. Fully functional, source-code complete software system deployed on a cloud serv...
I run a Windows-based desktop powered by an RTX 5090 and want to turn it into a reliable, local playground for the latest stable releases of Stability Matrix, Stable Diffusion, MidJourney, ComfyUI, and Kohya. I need more than a basic installer—I’d like the full environment properly configured, GPU-accelerated, and ready to create images the moment we finish. You’ll connect through a secure remote session, handle every dependency (CUDA, Python, libraries, checkpoints, etc.), and tune paths so each tool cooperates without conflicts. Where optional models or extensions improve usability, feel free to suggest and add them as long as they remain stable. Deliverables • All five applications installed in their most recent stable versions • Verified ability...
Note: This requires a Nvidia graphics card, please do not bid unless you have one I have a C# application, that will download trellis.2 and flux AI models and use them. Your task is simple, use the software and report any issues, i prefer screen share with discord
...from Freelancer The freelancer should: * independently choose the best AI workflow/pipeline, * use modern AI tools, * suggest the optimal production process, * upscale/enhance footage if necessary, * deliver finalized ready-to-publish videos. --- # Preferred Tools Possible tools include: * Runway * Kling * Veo * HeyGen * Midjourney * Flux * Stable Diffusion * ElevenLabs * LivePortrait * ComfyUI * or other modern AI tools --- # Final Deliverables Expected final result: * completed short-form videos, * stable AI avatar, * high-quality voice/lip sync, * cinematic motion, * ready for social media publishing. --- # Bonus Skills (Preferred) It is a plus if the freelancer can: * create a consistent character across scenes, * generate multiple emotions and camera angles, * ...
...generation Scheduling/posting Chat/reply assistance Fan engagement automation Content organization Preferred if you can build: Custom workflows AI prompting systems Automation dashboards Repeatable content templates 5. Technical Requirements Looking for someone experienced with tools/frameworks such as: Stable Diffusion / Flux LoRA training Face consistency workflows ComfyUI / Automatic1111 AI video tools Voice cloning (optional) Image upscaling/editing Prompt engineering Experience with adult-content-safe workflows and platform compliance is important. 6. Deliverables Expected deliverables include: Fully developed AI character Character reference pack Prompt library/workflows Image & video generation pipeline Branding kit I...
...character appearance across all content The videos should look highly realistic and believable, with accurate mouth synchronization to audio/dialogue. Experience with cinematic lighting, realism, and smooth motion is important. Requirements: * Experience with AI image/video generation workflows * Experience using LoRA models * Knowledge of tools such as: * Stable Diffusion / Flux * ComfyUI * AnimateDiff * Runway * Kling * Veo * SadTalker / LivePortrait / similar lip-sync tools * Ability to upscale and improve realism * Understanding of consistent character generation Deliverables: * High-resolution images * Short realistic video clips * Lip-synced talking clips * Organized source/project files if applicable Please include in your proposal: * Exa...
...AI-generated storybooks built in ComfyUI. Every story and its artwork already exist in separate pieces; what’s missing is a smooth pipeline that marries the two so each page displays the right image at the right moment. Inside ComfyUI you will: • Import my scanned or layered hand-drawn files, clean up any color or transparency issues, and convert them to the resolution ComfyUI expects. • Place each illustration in sequence, synchronising with the text nodes already in the workflow. • Configure any necessary image-to-text or text-overlay nodes so captions and dialogue stay crisp and legible on both tablet and print layouts. • Export a ready-to-publish package (JSON workflow + rendered page images in PNG and PDF). Acceptance criteri...
...face swap—the hair, build, posture, clothing, and subtle movements all have to follow the original performance while appearing 100 % natural and photorealistic. The source clip is already edited; you will receive the final cut in high-resolution along with still frames for reference. Feel free to work in whatever pipeline you prefer—Stable Video Diffusion, Runway Gen-2, DeepFaceLab, Houdini, ComfyUI, or a custom blend—as long as the end result is seamless and artifact-free when viewed frame by frame. Deliverables • Full-resolution transformed video in the same codec and frame rate as the original • A side-by-side comparison export for quick review • Project files or node graphs that allow future tweaks (so I’m not locked o...
...workflows Deliverables • 100 edited images • Same resolution as original JPEG and WEBP format • Clean, realistic, professional quality • No watermarks Required Skills The freelancer must have: 1. Strong experience with AI image editing Examples: • Adobe Photoshop with Generative Fill • Stable Diffusion (inpainting, ControlNet, IP Adapter) • Midjourney V6 (inpainting mode) • Runway Gen 2 • ComfyUI workflows 2. Ability to match colors, textures, and lighting • Outfits must look like real fabric • Logos must look printed or stitched • Helmet colors must blend naturally 3. Experience with human subjects • Skin tones • Shadows • Proportions • Avoiding uncanny AI artifacts AI Requirements (Equipment &a...
I’m ready to jump from scattered proofs-of-concept to a repeatable pipeline that lets me generate dramatic short videos in which the same character stays perfectly on-model from the first frame to the last. To do that, I need Stable Diffusion installed, optimised and running inside Comfy (ComfyUI / Comfy manager, whichever you prefer) on my local Windows workstation. Once it is up, I’ll rely on you to configure a workflow that feeds prompts, reference images and keyframes through the right nodes so that every shot of my drama-style “film” keeps facial features, clothing details and proportions consistent. Here’s what success looks like: • A fully operational Stable Diffusion environment integrated with Comfy that I can open, load your template ...
Ollama & comfyUI possibly already installed but receiving error message. May need re-install. Synology NAS, macbook Have some container issue. The goal for this session is simple: • Ollama and ComfyUI installed on the NAS, running reliably • Both services reachable from my MacBook via LAN for quick model tests
Job Title: AI Prompt Engineer – Generation of realistic Product showcase images Location: Remote (Freelance/Contract) About Us: We are a professional photography studio service, looking to get every image to look like a professional studio photograph—not AI art. The Role: You will build an agentic AI workflow (using tools like Midjourney, DALL·E, ComfyUI, or Stable Diffusion) to generate consistent, realistic watch images at scale. You will create prompts and automation that produce: Multiple angles of the same item Develop master prompts that generate photorealistic watch images. Create an automated or semi-automated workflow (e.g., using Python scripts, batch processing, or no-code tools) to generate product images from reference photos. Deliver images indis...
...Create images or scenes using Stable Diffusion (preferably via ComfyUI). Maintain consistent characters using LoRA models. Generate voice-over using AI (text-to-speech or voice cloning). Automatically assemble videos. Video requirements: Each video should be approximately 8 minutes long. The system should be able to generate longer-form content (not just shorts). Scenes should be sequenced to keep viewer engagement (not repetitive frames). Include background music and transitions. Add subtitles/captions automatically. Export ready-to-upload videos. Technical requirements: The system must run on Ubuntu (with GUI). It should be controllable remotely (via SSH or remote desktop like RustDesk). Prefer modular workflow (ComfyUI or similar node-based pipeline). Aut...
I need a 2-minute music video that looks live-action yet is fully generated with AI. The performance must feel realistic, keep perfect lip-sync with the song, and carry a light adventure storyline from start to finish. Here’s what I’m after: • A live-action-style video produced with tools such as ComfyUI, WAN, or Flux (if you use a different pipeline that reaches the same quality, let me know). • Visually coherent characters and environments that sell the illusion of footage shot on camera rather than animation. • Accurate facial movement and mouth shapes locked to my vocal track. • A clear beginning, middle, and end so the clip plays like a short adventure film rather than random imagery. I will supply the mastered 2-minute audio and any lyri...
...project is a solo-artist, concert-style performance set against realistic scenery. Throughout the entire song I want tight close-ups and mid shots that hold perfect lip-sync; smooth stitching between shorter AI-generated clips is completely fine as long as the audience never notices the joins. You are free to work in Runway Gen-2, Pika Labs, Stable Diffusion pipelines (AnimateDiff, ControlNet, ComfyUI, etc.), or any comparable solution that can deliver high-quality frames without compromising sync. Feel free to enhance the realism with subtle camera shake, depth-of-field, or stage lighting passes—anything that keeps the look grounded in a believable venue. Deliverables • Final 1920×1080 (4K welcomed if your workflow allows) video fully synced to my supplied W...
...shoots. My plan is to run an open-source diffusion model—Flux 2-dev or a similarly capable checkpoint—inside a rented RunPod GPU environment. Here’s the flow I need you to build and, once proven, hand off to me: • Spin up and configure the RunPod instance (A10 / A100 class or better), install the model, required weights, and supporting libraries (Diffusers, ControlNet, LoRA, Automatic1111 or ComfyUI—whichever you feel gives the cleanest control). • Design an image-to-image pipeline that takes my jewelry PNGs and merges them with a mix of model photographs I will supply, plus additional royalty-free images you will source when my library doesn’t cover a needed angle, pose, or skin tone. • Calibrate prompts, masks, and inpainting...
...Generated images are clearly anime-inspired, free of realism artifacts, and focused solely on human figures. 2. At least 10 sample outputs produced from my test prompts must meet the style guide (colour palette, line clarity, proportion). 3. All code runs end-to-end on my local RTX GPU without internet calls. Keywords you may lean on include Stable Diffusion, LoRA fine-tuning, ControlNet, ComfyUI, Diffusers, and Python. If you’ve previously trained anime generators or can show portfolio pieces proving stylistic accuracy, that will greatly speed up selection. Looking forward to seeing how you can bring this cartoon image engine to life....
...Front-facing body and face. Direct eye contact with camera. Natural smile or slight friendly expression. Ultra-realistic skin texture. Realistic anatomy. Clean and correct hands. Clean shoulders, posture, and body proportions. Plain, homogeneous background suitable for easy cutout. Output must work well for HeyGen Photo Avatars. Accepted Tools You may use Midjourney, Stable Diffusion, SDXL, Flux, ComfyUI, DALL·E, Photoshop, or a combined workflow. What matters is the final realism, consistency, and production quality. Important Quality Standards We are looking for someone who understands: photorealistic human generation. natural skin texture. realistic facial structure. realistic hands and anatomy correction. character consistency across multiple images. clean commerci...
...Animation: High-quality lip-syncing and fluid body movements. Environment: A clinical, laboratory-style automotive diagnostic hub (Amawbia/Awka workshop setting). Audio Integration: We will provide Pidgin English voice tracks (ElevenLabs clones). You must sync these perfectly. 4. DELIVERABLES Pilot Episode: One 30-second fully rendered 3D skit (MP4, 1080p or 4K). Source Assets: If using ComfyUI or similar, provide the workflow/LoRA used to maintain the faces. Consistency Guarantee: Documentation on how you will ensure Tokunbo’s gold tooth and OAT’s crossed eyes appear exactly the same in Episode 1 and Episode 10. 5. SELECTION CRITERIA Must demonstrate a portfolio with consistent AI characters (not just random one-off images). Proven experience in 3D st...
...educational videos. Furthermore, I have an AI-generated voice created through InVideo, which works wonderfully, and the scripts are easily modified. Moreover, I am generating infographics and animated data visualizations through Renderforest and laying this all over stock footage compiled with CapCut. Additionally, I have a 5090 GPU and a desktop that is more than capable of this work, but I admit the ComfyUI interface overwhelms me. As a corollary, I seek a workflow that efficiently generates realistic lip-synched avatars so I can produce my educational series and offer this service to my buyer agents as they join the team. Finally, I expect to require ongoing expertise and hope to form a strategic alliance with a strong freelancer in this area. I have a Sony a7r2 medium format ...
...workflow and no core dependency on paid APIs * Milestone-based delivery with real testing on our hardware * Clear folder structure, launch scripts, and reusable workflows * Full documentation, system map, and runbook * Simple launch process for daily use * Portable and clean system structure on a dedicated drive Who should apply Please apply only if you have real hands-on experience with: * ComfyUI * local AI video generation * facial / performance transfer * character consistency / identity locking * GPU-based local workflows * long-form or production-oriented video pipelines When applying, please send: * relevant examples of similar work * the tools you would use * how you would approach phase 1 * estimated timeline ...
PROJECT OVERVIEW I need an experienced ComfyUI specialist to set up a complete AI influencer content creation pipeline on (RTX 4090 / 24GB VRAM). The goal is a fully working environment where I can generate consistent AI character images (SFW and NSFW), short video clips, dance/motion transfer videos, and long-form talking head / UGC-style videos — all from ComfyUI. I will be training multiple character LoRAs, so all workflows must allow me to easily select which character to use from a dropdown before generating. Switching between characters should be as simple as picking a different LoRA file — no reconfiguration needed. I will handle LoRA training myself. I need you to build and configure the workflows, install all required models and custom nodes, and del...
...ad creatives, social assets, and concepts - Refine outputs to match enterprise brand standards - Build scalable design workflows - Scale into leading the design vertical What is Required - Proven ability to create high-quality AI-generated visuals - Strong design sense, composition, and aesthetics - Ability to deliver brand-consistent creative output Tools (Expected Expertise) - Midjourney, ComfyUI, , etc The Partnership - Profit-sharing model per project - No fixed salary - Opportunity to own the visual design vertical...
Complete end-to-end AI movie production pipeline: 1. Script Generation - AI generates script from your movie concept + duration 2. Character Generation - Consistent characters across all scenes 3. Scene Animation - AnimateDiff/...- AI generates script from your movie concept + duration 2. Character Generation - Consistent characters across all scenes 3. Scene Animation - AnimateDiff/SVD for video generation 4. Voice Synthesis - ElevenLabs for dialogue 5. Lip Sync - SadTalker/Wav2Lip integration 6. Auto-stitching - Final video assembly with transitions Deliverables: - n8n workflow ready to deploy on your local server - ComfyUI graphs optimized for 16:9 24fps - RunPod auto-scale setup - Complete documentation in Git repo You provide: movie concept + duration Pipeline handles: every...
...mind: 1. n8n receives the prompt (and optional reference image) and passes it to a RunPod or other cloud-GPU instance. 2. ComfyUI / Stable Diffusion creates the key frame. 3. AnimateDiff or SVD turns that image into a short video clip. 4. ElevenLabs API generates dialogue and ambience, then syncs it to the clip. 5. All assets—source prompt, still image, video, audio, and the final merged file—are saved in a dated scene folder that is mirrored to both Google Drive and Amazon S3. I already have accounts and API keys for the major services; what I need is the glue: • A clean, reusable n8n workflow with environment variables for keys and storage paths • Optimised ComfyUI graph(s) for image generation at 16:9, 24 fps compatibility • Script or c...
