AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

RX 7800 XT image benchmarks

313 reported configurations · 5 sources · 331 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 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
FLUX.1-devBF16 + INT8 weight-onlyModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
Diffusers + TorchAO Diffusers0.37.1 / TorchAO0.14.1 / torch2.9.1+rocm7.1.1
Backend
ROCm / HIP
OS
Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
1024 × 1024Batch 128 stepsBatch 1
128.3 s/imageTime / image · reported
4.58 s/stepCalculated · Pipeline time / step · reported · pipeline per stepDerived by source: total pipeline wall time / 28 steps, including VAE decode; not isolated denoising-step timing.
6.39 GBPeak VRAM · reported
Whole workflow · Warm
View
Report
Diffusion workflow
Qwen-Image-2512BF16Model reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
Gridline
Backend
Not reported
OS
Not reported
Parallelization
Single GPU
Memory
16 GB per GPU
Reported
Not reported
Full record →
1664 × 928Batch 150 stepsBatch 1
2,363.6 sReported time · reported
Timing details missing
View
Report
SD WebUI
juggernautxl_v9rdphoto2lightningQuant not reportedFamily reference ↗Text → imageRadeon RX 7800 XT1 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
4.68 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
Report
ComfyUI
FLUX.2 Klein 4BQuant not reportedModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Arch Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
2026-01-19
Full record →
Resolution not reported4 stepsBatch not reported
16.22 s/imageTime / image · reported
Cold · Timing details missing
View
Report
UL Procyon
Stable Diffusion XLFP16Model 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 →
1024 × 1024Batch 1100 stepsBatch 1
42.2 s/imageTime / image · reported
Whole workflow · Timing details missing
View
Report
Diffusion workflow
FLUX.1-devBF16 + INT8 weight-onlyModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
Diffusers + TorchAO Diffusers0.37.1 / TorchAO0.14.1 / torch2.9.1+rocm7.1.1
Backend
ROCm / HIP
OS
Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
1024 × 1024Batch 128 stepsBatch 1
88.5 s/imageTime / image · reported
3.16 s/stepCalculated · Pipeline time / step · reported · pipeline per stepDerived by source: total pipeline wall time / 28 steps, including VAE decode; not isolated denoising-step timing.
6.39 GBPeak VRAM · reported
Whole workflow · Warm
View
Report
SD WebUI
juggernautxl_v9rdphoto2lightningQuant not reportedFamily reference ↗Text → imageRadeon RX 7800 XT1 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
5.66 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
ComfyUI
FLUX.2 Klein 4BQuant not reportedModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Arch Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
2026-01-19
Full record →
Resolution not reported4 stepsBatch not reported
6.24 s/imageTime / image · reported
Warm · Timing details missing
View
Report
Diffusion workflow
FLUX.1-devBF16 + INT8 weight-onlyModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
Diffusers + TorchAO Diffusers0.37.1 / TorchAO0.14.1 / torch2.9.1+rocm7.1.1
Backend
ROCm / HIP
OS
Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
1024 × 1024Batch 128 stepsBatch 1
80 s/imageTime / image · reportedApproximate typical value.
2.9 s/stepCalculated · Pipeline time / step · reported · pipeline per stepDerived by source: total pipeline wall time / 28 steps, including VAE decode; not isolated denoising-step timing.
6.39 GBPeak VRAM · reported
Whole workflow · Warm
View
Report
SD WebUI
juggernautxl_v9rdphoto2lightningQuant not reportedFamily reference ↗Text → imageRadeon RX 7800 XT1 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
4.97 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
stable-diffusion.cpp / sd2R
FLUX.2 Klein 4BQuant not reportedModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
stable-diffusion.cpp c7d4a6035de8f20264a4675edc475db481ef2ccc
Backend
ROCm / HIP
OS
Arch Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
2026-01-19
Full record →
Resolution not reported4 stepsBatch not reported
10.27 s/imageTime / image · reported
1.84 s/stepStep time · reported
Timing details missing
View
Report
Diffusion workflow
FLUX.1-devBF16 + INT8 weight-onlyModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
Diffusers + TorchAO Diffusers0.37.1 / TorchAO0.14.1 / torch2.9.1+rocm7.1.1
Backend
ROCm / HIP
OS
Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
1024 × 1024Batch 128 stepsBatch 1
82.1 s/imageTime / image · reported
2.93 s/stepCalculated · Pipeline time / step · reported · pipeline per stepDerived by source: total pipeline wall time / 28 steps, including VAE decode; not isolated denoising-step timing.
12.57 GBPeak VRAM · reported
Whole workflow · Warm
View
Report
SD WebUI
illustriousxl_v01Quant not reportedFamily reference ↗Text → imageRadeon RX 7800 XT1 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
5.08 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
stable-diffusion.cpp / sd2R
FLUX.2 Klein 4BQuant not reportedModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
stable-diffusion.cpp fa61ea744d1a87fa26a63f8a86e45587bc9534d6
Backend
ROCm / HIP
OS
Arch Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
2026-01-19
Full record →
Resolution not reported4 stepsBatch not reported
22.09 s/imageTime / image · reported
4.83 s/stepStep time · reported
Timing details missing
View
Report
Diffusion workflow
FLUX.1-devFP16 + INT8 weight-onlyModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
Diffusers + TorchAO Diffusers0.37.1 / TorchAO0.14.1 / torch2.9.1+rocm7.1.1
Backend
ROCm / HIP
OS
Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
1024 × 1024Batch 128 stepsBatch 1
75.2 s/imageTime / image · reported
2.69 s/stepCalculated · Pipeline time / step · reported · pipeline per stepDerived by source: total pipeline wall time / 28 steps, including VAE decode; not isolated denoising-step timing.
12.57 GBPeak VRAM · reported
Whole workflow · Warm
View
Report
SD WebUI
illustriousxl_v01Quant not reportedFamily reference ↗Text → imageRadeon RX 7800 XT1 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
5.99 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
stable-diffusion.cpp / sd2R
FLUX.2 Klein 4BQuant not reportedModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
stable-diffusion.cpp c7d4a6035de8f20264a4675edc475db481ef2ccc
Backend
Vulkan
OS
Arch Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
2026-01-19
Full record →
Resolution not reported4 stepsBatch not reported
15.9 s/imageTime / image · reported
3.62 s/stepStep time · reported
Timing details missing
View
Report
Diffusion workflow
FLUX.1-devBF16 + INT8 weight-onlyModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
Diffusers + TorchAO Diffusers0.37.1 / TorchAO0.14.1 / torch2.9.1+rocm7.1.1
Backend
ROCm / HIP
OS
Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
Not reported
Full record →
1024 × 1024Batch 128 stepsBatch 1
144.9 s/imageTime / image · reported
5.18 s/stepCalculated · Pipeline time / step · reported · pipeline per stepDerived by source: total pipeline wall time / 28 steps, including VAE decode; not isolated denoising-step timing.
6.39 GBPeak VRAM · reported
Whole workflow · Warm
View
Report
SD WebUI
illustriousxl_v01Quant not reportedFamily reference ↗Text → imageRadeon RX 7800 XT1 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
5.09 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
stable-diffusion.cpp / sd2R
FLUX.2 Klein 4BQuant not reportedModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
stable-diffusion.cpp fa61ea744d1a87fa26a63f8a86e45587bc9534d6
Backend
Vulkan
OS
Arch Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
2026-01-19
Full record →
Resolution not reported4 stepsBatch not reported
23.32 s/imageTime / image · reported
Timing details missing
View
Report
SD WebUI
illustriousxl_v01Quant not reportedFamily reference ↗Text → imageRadeon RX 7800 XT1 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
5.42 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
ComfyUI
FLUX.2 Klein 9BQuant not reportedModel reference ↗Text → imageRadeon RX 7800 XT1 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Arch Linux
Parallelization
Not reported
Memory
16 GB per GPU
Reported
2026-01-19
Full record →
Resolution not reported4 stepsBatch not reported
26.93 s/imageTime / image · reported
Cold · Timing details missing
View
Report
SD WebUI
illustriousxl_v01Quant not reportedFamily reference ↗Text → imageRadeon RX 7800 XT1 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
5.97 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 313 configurations →

All image benchmarks · Methodology and source review