SDXL Turbo — 1-Step
Single step generation with SDXL Turbo. Instant previews for rapid iteration on 8GB cards.
About this workflow
SDXL Turbo with adversarial diffusion distillation generates usable previews in under 1 second. CFG 0 (disabled), Euler Ancestral sampler. Resolution capped at 512px for VRAM efficiency. Use this for concept validation before full renders.
Required Model
sd_xl_turbo_1.0_fp16.safetensors
Place in: ComfyUI/models/checkpoints/
Benchmark (RTX 5080)
Gen Time
~0.8s on RTX 5080
Resolution
512×512
Hardware Profile
Settings adjust to your GPU tier
16GB Recommended — Specs
Full quality. Recommended tier for this workflow.
Export Package
✓ Real ComfyUI node graph JSON
✓ Hardware settings baked in
✓ Launch flags in metadata note
✓ Load directly in ComfyUI
// Hardware
Not sure your rig can handle this? Plan your upgrade on ComputeAtlas.
Hardware Estimator →