SDXL Image-to-Image
Transform existing images with SDXL. Denoise 0.6 for strong style transfer while preserving composition.
About this workflow
Img2img workflow that re-renders your existing images with new style prompts. Denoise at 0.6 preserves ~40% of the original composition. Oil painting preset loaded. Encode input via VAEEncode, decode via VAEDecode. Swap the prompt to change output style entirely.
Required Model
sd_xl_base_1.0.safetensors
Place in: ComfyUI/models/checkpoints/
Benchmark (RTX 5080)
Gen Time
~5s on RTX 5080
Resolution
1024×1024
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 →