Anton Tenitsky

AI workflows, with the templates to run them.

I'm Anton, a 3D artist with more than 15 years in computer graphics. I've worked with Nickelodeon, with mobile game studio Gameloft, on Marvel Rivals and for many other clients. Today I'm using AI to build the next generation of computer graphics, and here I share exactly how I set everything up: open-source models, ComfyUI workflows, and templates on GitHub you can run yourself.

ComfyUI and RunPod logos: setting up ComfyUI in the cloud in under 10 minutes
Start here

Introduction to RunPod: running ComfyUI in the cloud

Why I moved ComfyUI from my own RTX A5000 to RunPod, what cloud GPUs cost, which GPU to pick for each job, and the setup from a network volume to your first render.

Read the guide →

New to RunPod? My referral link: sign up through it and you get $5–$500 in RunPod credits. Without a referral link there's no bonus. I get the same bonus and use it for compute.

Templates

Free on GitHub, ready to run on RunPod.
MiniMax H3 avatarsTested on RunPod

Long talking-head videos from one portrait and a folder of voiceovers.

GuideGitHubDeploy on RunPod
LTX-2.5 lip syncTested on RunPod

A talking avatar with lip sync from a single photo.

GuideGitHubDeploy on RunPod
Qwen3-TTS voiceoversTested locally

Nine voices, voice design and voice cloning in 10 languages.

GuideGitHub
SoulX-FlashHead ProTested on RunPod

Long 512 × 512 talking heads from one portrait on a single GPU.

GuideGitHubDeploy on RunPod
LongCat-Video-Avatar 1.5Tested on RunPod

Long-form talking avatars under the MIT licence.

GuideGitHubDeploy on RunPod
Stable Audio 3 sound FXTested on RunPod

Sound effects and music loops, one at a time or from a list.

GuideGitHubDeploy on RunPod
TRELLIS 2Tested on RunPod

Image to 3D model, in bulk.

GuideGitHubDeploy on RunPod
Z-Image TurboTested on RunPod

Fast, cheap image generation with LoRA and multi-image nodes.

GitHub
Prompt Cycler nodeTested on RunPod

A custom ComfyUI node that cycles through any number of prompts.

GuideGitHub

All guides, newest first

  1. Oct 30, 2026Four open-source talking-avatar models compared: cost per minute, render time and qualityVideo & avatars
  2. Oct 22, 2026Writing AI prompts by voice with Wispr FlowVoice & audio
  3. Oct 21, 2026Fast, cheap talking heads from one portrait with FlashHead Pro in ComfyUIVideo & avatars
  4. Oct 17, 2026High-quality talking avatars with LongCat-Video-Avatar 1.5: H100 vs RTX PRO 4500 costVideo & avatars
  5. Oct 13, 2026Free AI voiceovers with Qwen3-TTS in ComfyUI: 9 voices, voice design and cloningVoice & audio
  6. Oct 11, 2026Batch AI avatar videos from one photo with MiniMax H3 in ComfyUIVideo & avatars
  7. Sep 28, 2026A consistent talking avatar from one photo with LTX-2.5 lip sync in ComfyUIVideo & avatars
  8. Aug 28, 2026Generating sound effects in bulk with Stable Audio 3 in ComfyUIVoice & audio
  9. Aug 1, 2026Generating textured 3D models in bulk with TRELLIS 2 and ComfyUI3D generation
  10. Jul 21, 2026Hundreds of game assets in one consistent style with Z-Image, a LoRA and Meshy3D generation
  11. Jul 5, 2026Thousands of AI images for under $0.001 each with Z-Image Turbo in ComfyUIImage generation
  12. May 27, 2026Z-Image Turbo on RunPod: the quickest way to run it in ComfyUIImage generation
  13. May 20, 2026Introduction to RunPod: running ComfyUI in the cloudCloud GPUs
  14. Nov 29, 2025Batch concept art from photos with Flux and a depth ControlNet in ComfyUIImage generation
  15. Nov 6, 2025Batch-turn stock photos into cinematic AI art with SDXL on a 4 GB GPUImage generation
  16. Oct 30, 2025Prompt Cycler: run a list of prompts in ComfyUI, one per imageComfyUI basics
  17. Sep 12, 2025Apply an artist’s style to a Blender 3D scene with Flux, a LoRA and ComfyUIBlender + AI
  18. Sep 8, 2025How to train a LoRA on any artist’s style (Flux + ComfyUI)Style & LoRA training
  19. Sep 5, 2025Testing Google’s Nano Banana on real concept art: what works and what doesn’tImage generation
  20. Aug 27, 2025Auto-generate prompts from images in ComfyUI with a local vision modelComfyUI basics
  21. Jul 25, 2025Fix any part of an image with Flux inpainting in ComfyUI, one region at a timeFix & enhance
  22. Jul 18, 2025From a 3D blockout to a textured 3D model with AI: concept, shape and textureBlender + AI
  23. Jul 16, 2025An automated 3D-to-concept-art pipeline in ComfyUI: blockouts, prompt lists and auto-sortingBlender + AI
  24. Jul 15, 2025Sketch to AI art with Flux in ComfyUI, locally or in the cloudImage generation
  25. Jul 14, 2025Auto-fix AI faces and hands in hundreds of images with ComfyUI and FluxFix & enhance
  26. Jul 11, 2025Auto-crop thousands of photos around faces with AI in ComfyUIComfyUI basics
  27. Jul 9, 2025Prompt lists in ComfyUI: render one 3D blockout in dozens of art styles overnightBlender + AI
  28. Jul 8, 2025How to fix messed-up AI hands in ComfyUI with Flux inpaintingFix & enhance
  29. Jul 6, 2025Sort images by aspect ratio automatically in ComfyUI (a boolean switch, two ways)ComfyUI basics
  30. Jul 5, 2025Meme to monster: a photoreal Pepe with Flux, a depth map and one very long promptImage generation
  31. Jun 25, 2025Turn sketches into AI art on a 4 GB GPU with SDXL in ComfyUIImage generation
  32. Jun 14, 2025Run ComfyUI on your home PC from anywhere, in a browser, for freeComfyUI basics
  33. May 30, 2025Live AI concept art from Blender: design sci-fi guns with screen share, SDXL and ComfyUIBlender + AI
  34. Apr 15, 2025Real-time concept art from a Blender scene with Stable Diffusion and ComfyUIBlender + AI
  35. Feb 23, 2025Relight any photo with IC-Light in ComfyUI: prompts, light masks and detail transferFix & enhance
  36. Feb 12, 2025Style transfer in ComfyUI with IPAdapter: one image, then two and three combinedStyle & LoRA training
  37. Jan 31, 2025Mask anything by typing its name: Florence 2 masking and inpainting in ComfyUIFix & enhance
  38. Jan 27, 2025Stop colour bleeding in ComfyUI: prompt weights, Conditioning Concat and Conditioning AverageComfyUI basics
  39. Jan 23, 2025Free AI upscaling in ComfyUI with Ultimate SD Upscale and SD 1.5, even on 4 GB of VRAMFix & enhance
  40. Jan 15, 2025Install the ComfyUI Manager, then merge two images with image-to-imageComfyUI basics
  41. Jan 12, 2025ComfyUI for beginners: install it, then build a text-to-image workflow node by nodeComfyUI basics
  42. Jan 10, 2025A 3D prop in an AI-generated room: Blender 4.3, Stable Diffusion and camera projectionBlender + AI
  43. Nov 22, 2024From a Blender blockout to a finished AI render with a depth ControlNet, then back into 3DBlender + AI
  44. Mar 18, 2024Designing a concept car in Blender: from a low-poly blockout to a clean sub-D modelBlender + AI