ComfyUI Workflow Library

Each page lists models, sizes, VRAM estimate with source, nodes, and fixes.

• SDXL Base + Refiner text-to-image — ~6.94 GB VRAM (derived)
• Flux.1 Dev text-to-image — ~23.8 GB VRAM (derived)
• Flux.1 Schnell 4-step text-to-image — ~11.89 GB VRAM (derived)
• Flux Fill inpainting & outpainting — ~23.8 GB VRAM (derived)
• Flux Kontext image editing — ~23.8 GB VRAM (derived)
• SD 1.5 inpainting — ~4.26 GB VRAM (derived)
• ESRGAN model upscaling — ~0.07 GB VRAM (derived)
• AnimateDiff-Evolved text-to-video — ~6.08 GB VRAM (derived)
• Wan 2.1 text-to-video (1.3B) — ~8.19 GB VRAM (official)
• Wan 2.1 image-to-video (14B) — ~16.4 GB VRAM (derived)
• HunyuanVideo text-to-video — ~45 GB VRAM (official)
• LTX-Video text/image-to-video — ~9.37 GB VRAM (derived)