Best of Diffusion Models — 2025

1. 1
   Article

   Towards Data Science·1y

   Diffusion Models, Explained Simply

   Diffusion models are a core technique in generative AI, especially for image creation. They use forward diffusion to add random noise to an image and reverse diffusion to reconstruct the original image from the noisy version. Key components include the U-Net architecture, which preserves image dimensions and facilitates precise image reconstruction. The diffusion process involves training neural networks across multiple iterations, enabling effective image synthesis while balancing computational costs.

   37

   1
2. 2
   Article

   Hacker News·24w

   Tongyi-MAI/Z-Image

   Z-Image is a 6B parameter image generation model featuring three variants: Z-Image-Turbo (distilled for sub-second inference with 8 NFEs on H800 GPUs), Z-Image-Base (foundation model for fine-tuning), and Z-Image-Edit (specialized for image editing). Built on a Scalable Single-Stream DiT architecture, it excels at photorealistic generation, bilingual text rendering (English/Chinese), and instruction following. The model uses Decoupled-DMD distillation algorithm and DMDR (combining DMD with reinforcement learning) for few-step generation optimization. Available on Hugging Face and ModelScope with PyTorch and Diffusers support.

   25
3. 3
   Article

   Hugging Face·49w

   (LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

   QLoRA enables fine-tuning of FLUX.1-dev diffusion models on consumer hardware with under 10GB VRAM by combining 4-bit quantization with Low-Rank Adaptation. The approach uses bitsandbytes for quantization, 8-bit AdamW optimizer, gradient checkpointing, and cached latents to dramatically reduce memory usage from ~120GB to ~9GB. Training on RTX 4090 takes 41 minutes for 700 steps, while FP8 training with torchao on H100 reduces time to 20 minutes. The technique maintains high-quality results while making advanced model customization accessible to developers without enterprise-grade hardware.

   11