RX 7900 XT image benchmarks

173 reported configurations · 3 sources · 173 measurements

Documented results

24 selected configurations

Selected across sources, not a performance ranking. Match model weights, resolution, steps, software and timing scope before comparing.

Source	Model	GPUs	Output	Measurements
View ReportUL Procyon	Stable Diffusion 1.5FP16Model reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine UL Procyon AI Image Generation Backend ONNX Runtime / DirectML OS Windows Parallelization Not reported Memory 20 GB per GPU Reported 2025-06-04 Full record →	512 × 512Batch 4100 stepsBatch 4	3.6 s/imageTime / image · reported Whole workflow · Timing details missing
View ReportDiffusion workflow	SDXL 1.0 Base Olive optimizedQuant not reportedTested weights ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine ONNX Runtime / Microsoft Olive Backend DirectML OS Windows 11 Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	1024 × 1024Steps not reportedBatch not reported	3.8 steps/sSampling steps · reportedApproximate author-reported rate.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 1Steps not reportedBatch 1	1.7 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportUL Procyon	Stable Diffusion XLFP16Model reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine UL Procyon AI Image Generation Backend ONNX Runtime / DirectML OS Windows Parallelization Not reported Memory 20 GB per GPU Reported 2025-06-04 Full record →	1024 × 1024Batch 1100 stepsBatch 1	28.5 s/imageTime / image · reported Whole workflow · Timing details missing
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 2Steps not reportedBatch 2	2.03 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 4Steps not reportedBatch 4	1.65 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 1Steps not reportedBatch 1	7.68 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 2Steps not reportedBatch 2	11.37 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 4Steps not reportedBatch 4	11.55 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 1Steps not reportedBatch 1	7.88 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 2Steps not reportedBatch 2	11.35 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 3cf53018 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 4Steps not reportedBatch 4	11.61 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	juggernautxl_juggxibyrundiffusionQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next 586ef9a3 Backend ROCm / HIP OS Linux Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 1Steps not reportedBatch 1	4.78 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	juggernautxl_juggxibyrundiffusionQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next 586ef9a3 Backend ROCm / HIP OS Linux Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 2Steps not reportedBatch 2	1.45 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	juggernautxl_juggxibyrundiffusionQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next 586ef9a3 Backend ROCm / HIP OS Linux Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 4Steps not reportedBatch 4	1.52 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	smoothmixillustrious_illustriousv2Quant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next cb0eb555 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 1Steps not reportedBatch 1	6.15 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	smoothmixillustrious_illustriousv2Quant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next cb0eb555 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 2Steps not reportedBatch 2	8.59 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	smoothmixillustrious_illustriousv2Quant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next cb0eb555 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 4Steps not reportedBatch 4	9.85 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	juggernautxl_juggxibyrundiffusionQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next 431bcc36 Backend ROCm / HIP OS Linux Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 1Steps not reportedBatch 1	7.52 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	juggernautxl_juggxibyrundiffusionQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next 431bcc36 Backend ROCm / HIP OS Linux Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 2Steps not reportedBatch 2	1.51 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	juggernautxl_juggxibyrundiffusionQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine SD.Next 431bcc36 Backend ROCm / HIP OS Linux Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 4Steps not reportedBatch 4	1.55 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 04bf93f1 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 1Steps not reportedBatch 1	6.87 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 04bf93f1 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 2Steps not reportedBatch 2	11.21 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.
View ReportSD WebUI	sd_xl_base_1.0_0.9vae.safetensorsQuant not reportedFamily reference ↗Text → image	Radeon RX 7900 XT1 GPU Configuration Engine Stable Diffusion WebUI 04bf93f1 Backend ZLUDA OS Windows Parallelization Not reported Memory 20 GB per GPU Reported Not reported Full record →	512 × 512Batch 4Steps not reportedBatch 4	11.87 image-steps/sPipeline throughput · reportedHarness computes steps times batch divided by process_images wall time; not sampler iterations per second or images per second.

Explore all 173 configurations →

All image benchmarks · Methodology and source review