SDXL Batch ×8 Grid
8 simultaneous variations at 768×768. Product design and concept iteration at scale.
About this workflow
Maximum batch workflow at 8 images per run. Reduced to 768×768 to fit 8 latents in 12GB VRAM. Product design prompts pre-loaded for concept exploration. Run once, get 8 different interpretations to select from. Pair with image grid viewer for comparison.
Required Model
sd_xl_base_1.0.safetensors
Place in: ComfyUI/models/checkpoints/
Benchmark (RTX 5080)
Gen Time
~20s on RTX 5080
Resolution
768×768
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 →