RX 9070 XT image benchmarks

256 reported configurations · 10 sources · 267 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 9070 XT1 GPU Configuration Engine UL Procyon AI Image Generation Backend ONNX Runtime / DirectML OS Windows Parallelization Not reported Memory 16 GB per GPU Reported 2025-06-04 Full record →	512 × 512Batch 4100 stepsBatch 4	2.4 s/imageTime / image · reported Whole workflow · Timing details missing
View ReportDiffusion workflow	RedCraft 3.0 Krea2 INT4 ConvRotINT4 ConvRotTested weights ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine InvokeAI 6.14.0 Backend ROCm / HIP OS Windows 11 Pro Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 18 stepsBatch 1	41.21 s/imageTime / image · median Whole workflow · Cold · median
View ReportComfyUI	Qwen-Image2.1Q8_0Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Windows11 Pro build26200 Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 120 stepsBatch 1	294.7 s/imageTime / image · reported 15.88 GiBPeak VRAM · reportedPeak allocated, as reported; preserveGiB unit. Whole workflow · Cold
View ReportComfyUI	Stable Diffusion XLQuant not reportedModel reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend Not reported OS Ubuntu Linux Parallelization Not reported Memory 16 GB per GPU Reported 2026-09-23 Full record →	1024 × 1024Batch 130 stepsBatch 1	0.137 images/sCalculated · Image rate · reported · sustained pipeline throughputExact unit normalization of reported8.22images/minute.reported images per minute / 60
View ReportDiffusion workflow	Stable Diffusion XLFP8Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine SHARK / Shortfin / IREE Backend ROCm / HIP OS Ubuntu Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	Resolution not reportedSteps not reportedBatch not reported	3.4 s/imageTime / image · reported Whole workflow · Timing details missing
View ReportComfyUI	Stable Diffusion 1.5FP16Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI 0.38.0 Backend ROCm / HIP OS Windows 11 Home 26200 Parallelization Single GPU Memory 16 GB per GPU Reported 2026-10-12 Full record →	512 × 512Batch 820 stepsBatch 8	7.58 s/batchBatch time · mean Timing details missing · mean
View ReportComfyUI	Stable Diffusion 1.5Quant not reportedModel reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Kubuntu 20.04 (as reported) Parallelization Not reported Memory 16 GB per GPU Reported 2025-03-21 Full record →	512 × 51220 stepsBatch not reported	4.16 s/imageTime / image · reported 6.25 steps/sSampling steps · reported Timing details missing
View ReportComfyUI	Qwen-Rapid-AIO v22Quant not reportedModel reference ↗Image editing	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Ubuntu 24.04 LTS Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	2040 × 13604 stepsBatch not reported	56.9 s/imageTime / image · reported Cold · Timing details missing
View ReportSD WebUI	tempestv0.1-artisticQuant not reportedFamily reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine SD.Next 6633e8e5 Backend ZLUDA OS Windows Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	512 × 512Batch 1Steps not reportedBatch 1	2.04 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 ReportComfyUI	Krea 2 derivative with LoRAs (unspecified)INT8 ConvRotFamily reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Linux Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	Resolution not reportedSteps not reportedBatch not reported	25 s/imageTime / image · range lower 28 s/imageTime / image · range upper Timing details missing · range lower
View ReportUL Procyon	Stable Diffusion XLFP16Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine UL Procyon AI Image Generation Backend ONNX Runtime / DirectML OS Windows Parallelization Not reported Memory 16 GB per GPU Reported 2025-06-04 Full record →	1024 × 1024Batch 1100 stepsBatch 1	18.3 s/imageTime / image · reported Whole workflow · Timing details missing
View ReportDiffusion workflow	RedCraft 3.0 Krea2 INT4 ConvRotINT4 ConvRotTested weights ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine InvokeAI 6.14.0 Backend ROCm / HIP OS Windows 11 Pro Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 18 stepsBatch 1	8.73 s/imageTime / image · median 1.05 steps/sSampling steps · reported Whole workflow · Warm · median
View ReportComfyUI	Qwen-Image2.1Q8_0Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Windows11 Pro build26200 Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 120 stepsBatch 1	40.4 s/imageTime / image · reported 15.88 GiBPeak VRAM · reportedPeak allocated, as reported; preserveGiB unit. Whole workflow · Warm
View ReportDiffusion workflow	Stable Diffusion XLINT8Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine SHARK / Shortfin / IREE Backend ROCm / HIP OS Ubuntu Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	Resolution not reportedSteps not reportedBatch not reported	3.9 s/imageTime / image · reported Whole workflow · Timing details missing
View ReportComfyUI	Stable Diffusion 1.5FP16Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI 0.38.0 Backend ROCm / HIP OS Windows 11 Home 26200 Parallelization Single GPU Memory 16 GB per GPU Reported 2026-10-12 Full record →	512 × 512Batch 820 stepsBatch 8	4.73 s/batchBatch time · mean Timing details missing · mean
View ReportComfyUI	Stable Diffusion XLQuant not reportedModel reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Kubuntu 20.04 (as reported) Parallelization Not reported Memory 16 GB per GPU Reported 2025-03-21 Full record →	1024 × 102420 stepsBatch not reported	32.25 s/imageTime / image · reported 1.03 steps/sSampling steps · reported Timing details missing
View ReportComfyUI	Qwen-Rapid-AIO v22Quant not reportedModel reference ↗Image editing	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Ubuntu 24.04 LTS Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	2040 × 13604 stepsBatch not reported	41.8 s/imageTime / image · reported Warm · Timing details missing
View ReportSD WebUI	tempestv0.1-artisticQuant not reportedFamily reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine SD.Next 6633e8e5 Backend ZLUDA OS Windows Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	512 × 512Batch 2Steps not reportedBatch 2	2.47 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 ReportComfyUI	Krea 2 derivative with LoRAs (unspecified)INT8 ConvRotFamily reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Linux Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	Resolution not reportedSteps not reportedBatch not reported	98 s/imageTime / image · range lower 229 s/imageTime / image · range upper Timing details missing · range lower
View ReportDiffusion workflow	Anima Turbo v1.1Quant not reportedTested weights ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine InvokeAI 6.14.0 Backend ROCm / HIP OS Windows 11 Pro Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 18 stepsBatch 1	14.64 s/imageTime / image · median Whole workflow · Cold · median
View ReportComfyUI	Qwen-Image2.1INT8 ConvRotTested weights ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Windows11 Pro build26200 Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	1024 × 1024Batch 120 stepsBatch 1	155.9 s/imageTime / image · reported 15.82 GiBPeak VRAM · reportedPeak allocated, as reported; preserveGiB unit. Whole workflow · Cold
View ReportDiffusion workflow	Stable Diffusion XLFP16Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine IREE SDXL scripts Backend ROCm / HIP OS Not reported Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	Resolution not reportedSteps not reportedBatch not reported	0.217 s/forwardCalculated · Model forward time · reported · Model componentExact ms-to-seconds conversion; isolated UNet, not image latency.reported milliseconds / 1000 Model component · Timing details missing
View ReportComfyUI	Stable Diffusion 1.5FP16Model reference ↗Text → image	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI 0.38.0 Backend ROCm / HIP OS Windows 11 Home 26200 Parallelization Single GPU Memory 16 GB per GPU Reported 2026-10-12 Full record →	512 × 512Batch 820 stepsBatch 8	7.24 s/batchBatch time · mean Timing details missing · mean
View ReportComfyUI	Qwen-Rapid-AIO v22Quant not reportedModel reference ↗Image editing	Radeon RX 9070 XT1 GPU Configuration Engine ComfyUI Backend ROCm / HIP OS Ubuntu 24.04 LTS Parallelization Not reported Memory 16 GB per GPU Reported Not reported Full record →	2040 × 13604 stepsBatch not reported	59.8 s/imageTime / image · reported Cold · Timing details missing

Explore all 256 configurations →

All image benchmarks · Methodology and source review