300|Schedulers compared by the numbers
300|Guidance rescale and CFG variants
200|Reading cross-attention maps
300|Video VAEs: causal 3D compression
300|Audio diffusion: latents you can hear
300|Quantization choices: fp8, int8 and GGUF
300|How LoRA training really works
200|ControlNet versus IP-Adapter conditioning
400|Consistency models from first principles
200|Sub-graphs and App Mode in ComfyUI
300|Offloading and tiled decode: fitting big models
200|Seeds across samplers: what stays the same
