SDXL Batch ×4 Variations
Generate 4 variations simultaneously. Concept art prompts pre-loaded. Same seed, 4 outputs.
About this workflow
Batch generation workflow with EmptyLatentImage set to batch_size=4. Generates 4 images in a single forward pass — 4x the output for similar compute time. Pre-loaded with concept art variation prompts. Each of the 4 images uses the same seed with batch index variation.
Required Model
sd_xl_base_1.0.safetensors
Place in: ComfyUI/models/checkpoints/
Benchmark (RTX 5080)
Gen Time
~12s 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 →