AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

Stable Diffusion image benchmarks on AMD GPUs

777 reported configurations · 9 sources · 780 measurements

Documented results

24 selected configurations

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

SourceModelGPUsOutputMeasurements
View
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon RX 7700 XT1 GPU
Configuration
Engine
UL Procyon AI Image Generation
Backend
ONNX Runtime / DirectML
OS
Windows
Parallelization
Not reported
Memory
12 GB per GPU
Reported
2025-06-04
Full record →
512 × 512Batch 4100 stepsBatch 4
5.4 s/imageTime / image · reported
Whole workflow · Timing details missing
View
Report
Diffusion workflow
Stable Diffusion 1.5Quant not reportedModel reference ↗UnknownRadeon PRO W78001 GPU
Configuration
Engine
Automatic1111 (AMD DirectML fork) 1.3.1
Backend
DirectML
OS
Windows 11 Pro 22621
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2023-07-31
Full record →
512 × 512Batch 1200 stepsBatch 1
3.29 steps/sSampling steps · reportedGeometric mean across text-to-image and image-to-image; not a single image latency or arithmetic mean.
View
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon RX 9070 GRE1 GPU
Configuration
Engine
UL Procyon AI Image Generation
Backend
ONNX Runtime / DirectML
OS
Windows
Parallelization
Not reported
Memory
12 GB per GPU
Reported
Not reported
Full record →
Resolution not reportedSteps not reportedBatch not reported
3.1 s/imageTime / image · reported
Timing details missing
View
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon PRO W77001 GPU
Configuration
Engine
UL Procyon
Backend
Not reported
OS
Windows
Parallelization
Single GPU
Memory
16 GB per GPU
Reported
2025-10-20
Full record →
Resolution not reportedSteps not reportedBatch not reported
902 pointsProcyon performance index · reportedUL Procyon AI Image Generation SD 1.5 FP16 score; higher is better. Not a time or quality score.
View
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon RX 9070 GRE1 GPU
Configuration
Engine
UL Procyon AI Image Generation
Backend
Not reported
OS
Not reported
Parallelization
Not reported
Memory
12 GB per GPU
Reported
2026-06-02
Full record →
Resolution not reportedSteps not reportedBatch not reported
3.238 s/imageTime / image · reported
1,930 Procyon scoreProcyon performance index · reportedPerformance score, not image quality.
Timing details missing
View
Report
ComfyUI
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon 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
Report
ComfyUI
Stable Diffusion 1.5Quant not reportedModel reference ↗Text → imageRadeon 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
Report
SD WebUI
sd1.5\epicphotogasm_xphotorealQuant not reportedFamily reference ↗Text → imageRadeon RX 7900 GRE1 GPU
Configuration
Engine
SD.Next 3f360891
Backend
ZLUDA
OS
Windows
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
512 × 512Batch 1Steps not reportedBatch 1
7.61 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
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon RX 9060 XT1 GPU
Configuration
Engine
UL Procyon AI Image Generation
Backend
Not reported
OS
Not reported
Parallelization
Not reported
Memory
16 GB per GPU
Reported
2025-06-04
Full record →
Resolution not reportedSteps not reportedBatch not reported
4.352 s/imageTime / image · reported
1,436 Procyon scoreProcyon performance index · reportedPerformance score, not image quality.
Timing details missing
View
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon RX 7800 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
5 s/imageTime / image · reported
Whole workflow · Timing details missing
View
Report
Diffusion workflow
Stable Diffusion 2.1 baseQuant not reportedModel reference ↗UnknownRadeon PRO W78001 GPU
Configuration
Engine
SHARK 20230701_796
Backend
Vulkan / IREE
OS
Windows 11 Pro 22621
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2023-07-31
Full record →
512 × 512Batch 1200 stepsBatch 1
5.64 steps/sSampling steps · reportedGeometric mean across text-to-image and image-to-image; not a single image latency or arithmetic mean.
View
Report
ComfyUI
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon 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
Report
SD WebUI
sd1.5\epicphotogasm_xphotorealQuant not reportedFamily reference ↗Text → imageRadeon RX 7900 GRE1 GPU
Configuration
Engine
SD.Next 3f360891
Backend
ZLUDA
OS
Windows
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
512 × 512Batch 2Steps not reportedBatch 2
8.79 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
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon RX 7900 GRE1 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
4.1 s/imageTime / image · reported
Whole workflow · Timing details missing
View
Report
Diffusion workflow
Stable Diffusion 1.5Quant not reportedModel reference ↗UnknownRadeon PRO W79001 GPU
Configuration
Engine
Automatic1111 (AMD DirectML fork) 1.3.1
Backend
DirectML
OS
Windows 11 Pro 22621
Parallelization
Single GPU
Memory
48 GB per GPU
Reported
2023-07-31
Full record →
512 × 512Batch 1200 stepsBatch 1
4.14 steps/sSampling steps · reportedGeometric mean across text-to-image and image-to-image; not a single image latency or arithmetic mean.
View
Report
ComfyUI
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon 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
Report
SD WebUI
sd1.5\epicphotogasm_xphotorealQuant not reportedFamily reference ↗Text → imageRadeon RX 7900 GRE1 GPU
Configuration
Engine
SD.Next 3f360891
Backend
ZLUDA
OS
Windows
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
512 × 512Batch 4Steps not reportedBatch 4
9.65 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
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon 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
Report
Diffusion workflow
Stable Diffusion 2.1 baseQuant not reportedModel reference ↗UnknownRadeon PRO W79001 GPU
Configuration
Engine
SHARK 20230701_796
Backend
Vulkan / IREE
OS
Windows 11 Pro 22621
Parallelization
Single GPU
Memory
48 GB per GPU
Reported
2023-07-31
Full record →
512 × 512Batch 1200 stepsBatch 1
18.53 steps/sSampling steps · reportedGeometric mean across text-to-image and image-to-image; not a single image latency or arithmetic mean.
View
Report
ComfyUI
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon 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
4.39 s/batchBatch time · mean
Timing details missing · mean
View
Report
SD WebUI
sd1.5\epicphotogasm_xphotorealQuant not reportedFamily reference ↗Text → imageRadeon RX 7900 GRE1 GPU
Configuration
Engine
SD.Next 3f360891
Backend
ZLUDA
OS
Windows
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
512 × 512Batch 1Steps not reportedBatch 1
3.05 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
Report
UL Procyon
Stable Diffusion 1.5FP16Model reference ↗Text → imageRadeon RX 7900 XTX1 GPU
Configuration
Engine
UL Procyon AI Image Generation
Backend
ONNX Runtime / DirectML
OS
Windows
Parallelization
Not reported
Memory
24 GB per GPU
Reported
2025-06-04
Full record →
512 × 512Batch 4100 stepsBatch 4
3.1 s/imageTime / image · reported
Whole workflow · Timing details missing
View
Report
ComfyUI
Juggernaut XL RagnarokQuant not reportedFamily reference ↗Text → imageRadeon 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 →
1024 × 1024Batch 130 stepsBatch 1
9.9 sReported time · mean
Timing details missing · mean
View
Report
SD WebUI
sd1.5\epicphotogasm_xphotorealQuant not reportedFamily reference ↗Text → imageRadeon RX 7900 GRE1 GPU
Configuration
Engine
SD.Next 3f360891
Backend
ZLUDA
OS
Windows
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
512 × 512Batch 2Steps not reportedBatch 2
3.31 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 777 configurations →

All image benchmarks · Methodology and source review