Nerdy Rodent Courses

Image to Video Generation with Nvidia Cosmos in ComfyUI

Discover how to transform static images into dynamic videos using Nvidia Cosmos and ComfyUI, with practical steps for home implementation requiring only 12GB VRAM.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Three AI Image Generation Models for Lower-End GPUs - Lumina, TinyBreaker, and Animagine XL

Discover three efficient AI image generation models - Lumina 2.0, TinyBreaker, and Animagine XL 4 - optimized for lower-end GPUs while delivering impressive results and faster processing times.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

SkyReels-V1: Text and Image to Video Generation in ComfyUI

Discover how to generate AI videos from text and images using SkyReels-V1 models in ComfyUI, with practical demonstrations and implementation tips for local video creation on consumer GPUs.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

HiDream - Now With Native ComfyUI Support

Discover how to use HiDream in ComfyUI with native support, exploring various text encoders and options like FP8 and GGUF without installing custom nodes, potentially achieving better image quality.

• YouTube
• 12 minutes
• Self-Paced
• Free Video

LTXV 0.97 - TURBO AI Video Generation at Home

Discover how LTXV 0.97 delivers ultra-fast AI video generation on consumer hardware, featuring real-time generation, upscaling, image-to-video conversion, and keyframe support in ComfyUI with minimal VRAM requirements.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

ACE-Step - A Step Towards a Foundational Music Generation Model

Explore ACE-Step, a free open-source text-to-music generator with inpainting capabilities, running on minimal hardware with lightning-fast generation times. Learn how to implement this foundational music model through ComfyUI or Gradio interface.

• YouTube
• 20 minutes
• Self-Paced
• Free Video

Amazing AI Video Natively in ComfyUI

Discover how to create AI video clips using ComfyUI's native support for WAN 2.1 VACE models, including text-to-image, video outpainting, and control features for both small and large VRAM systems.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

Animate Images Using Depth Maps with DepthFlow in ComfyUI

Master the art of creating 2.5D parallax animations from static images using DepthFlow in ComfyUI, featuring custom controls and efficient VRAM usage for quick, professional-quality animated outputs.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Style Images with HiDream in ComfyUI

Explore HiDream's powerful image-to-image capabilities in ComfyUI to transform photos to anime, create style hybrids, and master techniques like inpainting with effective prompting and denoise settings.

• YouTube
• 13 minutes
• Self-Paced
• Free Video

Multiple Characters in AI Videos - Just from their Images in ComfyUI

Discover how to create AI videos with multiple consistent characters using just single images per character with the new Phantom 14B model in ComfyUI.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Creating Consistent Characters for WAN AI Video

Discover how to create ideal datasets for WAN LoRA training in ComfyUI, focusing on character interactions and plain backgrounds for better results with both 1.3B and 14B versions.

• YouTube
• 16 minutes
• Self-Paced
• Free Video

Fast Video-to-Video with WAN and Loom in ComfyUI

Discover how to perform fast video-to-video transformations in ComfyUI using Loom nodes with WAN 2.1 1.3B, requiring less than 8GB VRAM and processing 81 frames in under 2 minutes on a 3090 GPU.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Hunyuan Video Installation and Usage Guide in ComfyUI

Master Hunyuan Video implementation in ComfyUI to create AI-generated videos from text prompts or video-to-video transformations, with minimal 8GB VRAM requirements and practical installation guides.

• YouTube
• 11 minutes
• Self-Paced
• Free Video

Regional LoRA Composition with ComfyUI's New Nodes

Master ComfyUI's new nodes for applying multiple LoRAs to different image regions, using hooks and combine nodes to create efficient regional prompting workflows and enhanced compositions.

• YouTube
• 10 minutes
• Self-Paced
• Free Video

YuE - Local AI Music Generation with Audio Prompts

Discover how to generate AI music locally using YuE's open-source tool - create custom tracks with audio prompts, separate stems, and minimal hardware requirements for creative music production.

• YouTube
• 14 minutes
• Self-Paced
• Free Video