ArtificialGuyBR

Home / Blog / AI video

AI video

WAN, HunyuanVideo and the speed tricks that make local video generation practical.

4 articles

HunyuanVideo: FP8 vs BF16, ComfyUI Setup, LoRA Training

Pick the right HunyuanVideo model file for your GPU, configure ComfyUI, and train a video LoRA.

Faster Local Video with SageAttention & TeaCache

Compare five acceleration techniques for ComfyUI video workflows — benchmarks, trade-offs, and install steps for each method.

PYTORCH_CUDA_ALLOC_CONF and VRAM Optimization

Fix CUDA OOM with PYTORCH_CUDA_ALLOC_CONF, optimize FLUX training with blocks_to_swap, and run Wan2.1 and HunyuanVideo on 12 GB GPUs.

Wan 2.2 High Noise vs Low Noise LoRA Workflow

Sequential ComfyUI chain: high-noise KSampler feeds low-noise KSampler. Correct LoraLoaderModelOnly setup and training guide.

Training LoRAsModels of 2026ComfyUIPrompting and controlFixing things

← All articles