Advanced Image Generation
Control image generation with ControlNet, LoRA training, and ComfyUI workflows.
0%
Confidence · no data yet
After this skill you can…
- Use ControlNet for pose/depth-guided generation
- Train a LoRA on your own subject
- Build a ComfyUI node workflow
Prerequisites
Watch (10 videos)
What is U-Net in Diffusion Models? #diffusionwithav #learnwithav #generativeai #diffusion
→ Implement U-Net in diffusion models→ Train U-Net for image generation tasks
Image-to-Image AI Art with Stable Diffusion Tutorial with Hugging Face Diffusers
→ Create image-to-image AI art using Stable Diffusion→ Use Hugging Face Diffusers for AI image generation
DREAMBOOTH: Train Stable Diffusion With Your Own Face And Style Together!
→ Generate custom AI art→ Fine-tune a diffusion model
Advanced Architectural Modeling and Texturing
→ Use Blender to create complex 3D scenes→ Optimize textures for realistic rendering
Midjourney's NEW REMIX mode: Everything You Need to Know
→ Use stable diffusion for upscaling→ Combine Midjourney with stable diffusion
FAST SD3.5 GGUF for low VRAM GPUs with Highest Quality. Stable Diffusion 3.5 Large, Turbo & Medium.
→ Fine-tune image generation models→ Improve GPU performance
Must Have Extensions for Stable Diffusion UI
→ Generate realistic images using Stable Diffusion→ Customize Stable Diffusion UI with extensions
Stable diffusion dreams of psychedelic faces
→ Use spherical interpolation for smooth image transitions→ Optimize image generation with GPU rendering
Learn to Create Portraits from Scratch with Advanced Diffusion Models
→ Generate portraits using diffusion models→ Implement advanced image generation techniques
Google’s New AI Watched 30,000,000 Videos!
→ Use space-time diffusion models for video generation→ Apply in-painting techniques to videos
DeepCamp AI