5 + VERSION2SPECS = { 6 + "SDXL-Turbo": { 7 + "H": 512, 8 + "W": 512, 9 + "C": 4, 10 + "f": 8, 11 + "is_legacy": False, 12 + "config": "configs/inference/sd_xl_base.yaml", 13 + "ckpt": "checkpoints/sd_xl_turbo_1.0.safetensors", 14 + ...
These are the same specs used in our demo Space. Batch SizeLatencyPerf/$ TPU v5e-4 (JAX) 4 2.33s 21.46 8 4.99s 20.04 TPU v4-8 (JAX) 4 2.16s 9.05 8 4.17 8.98 TPU v5e achieves up to 2.4x greater perf/$ on SDXL compared to TPU v4, demonstrating the cost-efficiency of...
A computer with specs good enough to run Fooocus, and proprietary Nvidia drivers Docker, Docker Compose, or Podman Quick start More information in the notes. Running with Docker Compose Clone this repository Run the docker container with docker compose up. Running with Docker docker run -p 7865...
Specs sound awesome, but not sure if camera will perform well enough, especially in low light, and the price... c'mon google, the price is just not worth it. I'm sure there will soon newer flagship phones with better specs and lower prices. ReplySony...
These are the same specs used in our demo Space. Batch SizeLatencyPerf/$ TPU v5e-4 (JAX) 4 2.33s 21.46 8 4.99s 20.04 TPU v4-8 (JAX) 4 2.16s 9.05 8 4.17 8.98 TPU v5e achieves up to 2.4x greater perf/$ on SDXL compared to TPU v4, demonstrating the cost-efficiency of the ...
These are the same specs used in our demo Space.Batch SizeLatencyPerf/$ TPU v5e-4 (JAX) 4 2.33s 21.46 8 4.99s 20.04 TPU v4-8 (JAX) 4 2.16s 9.05 8 4.17 8.98TPU v5e achieves up to 2.4x greater perf/$ on SDXL compared to TPU v4, demonstrating the cost-efficiency of the latest...
These are the same specs used in our demo Space.Batch SizeLatencyPerf/$ TPU v5e-4 (JAX) 4 2.33s 21.46 8 4.99s 20.04 TPU v4-8 (JAX) 4 2.16s 9.05 8 4.17 8.98TPU v5e achieves up to 2.4x greater perf/$ on SDXL compared to TPU v4, demonstrating the cost-efficiency of the latest...
These are the same specs used in our demo Space.Batch SizeLatencyPerf/$ TPU v5e-4 (JAX) 4 2.33s 21.46 8 4.99s 20.04 TPU v4-8 (JAX) 4 2.16s 9.05 8 4.17 8.98TPU v5e achieves up to 2.4x greater perf/$ on SDXL compared to TPU v4, demonstrating the cost-efficiency of the latest...
These are the same specs used in our demo Space. Batch SizeLatencyPerf/$ TPU v5e-4 (JAX) 4 2.33s 21.46 8 4.99s 20.04 TPU v4-8 (JAX) 4 2.16s 9.05 8 4.17 8.98 TPU v5e achieves up to 2.4x greater perf/$ on SDXL compared to TPU v4, demonstrating the cost-efficiency of the ...
These are the same specs used in our demo Space. Batch SizeLatencyPerf/$ TPU v5e-4 (JAX) 4 2.33s 21.46 8 4.99s 20.04 TPU v4-8 (JAX) 4 2.16s 9.05 8 4.17 8.98 TPU v5e achieves up to 2.4x greater perf/$ on SDXL compared to TPU v4, demonstrating the cost-efficiency of the ...