ComfyUI Jobs

Realistic AI Avatar Artist Needed for HeyGen – Original Work Only We are looking for a highly skilled AI image creator / prompt engineer / retoucher to produce ultra-realistic human avatars for commercial use in HeyGen. This is not a stylized, cartoon, fantasy, or artistic portrait project. We need photorealistic avatars that look like real people, with natural skin texture, realistic proportions, clean hands, premium facial detail, and a commercial-quality result suitable for avatar-based video generation. Project Goal We need highly realistic male and female avatars, approximately 26 years old, created for use in HeyGen. The final images must be suitable for half body and full body use, with the subject facing straight toward the camera, eyes looking directly into the lens, and...

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 funcionales qu...

I want a reproducible AI model that can take my raw portraits and return a polished, high-end beauty retouch that mirrors my own editing style. Think pristine yet realistic skin, flawless blemish removal and nuanced tonal work—no plasticky faces or over-smoothed texture. My current workflow lives in Photoshop and Capture One, but I’m open to any backend that gives the best fidelity; LoRA FLuX on a Stable Diffusion base has caught my eye, though I’m happy for you to suggest a stronger alternative if you can prove the advantage. What I will hand over • A curated set of before-and-after TIFFs/JPEGs—consistent lighting, color-managed, already retouched by me. What I need back • The trained model weights (.safetensors or compatible) ready to drop into...