AMD-Pro-BenchCommunity

13,812 benchmarks in 32 GPU combinations documented

HunyuanVideo video benchmarks on AMD GPUs

9 reported configurations · 2 sources · 9 measurements

Explore all resultsDataset

Documented results

9 selected configurations

Selected across sources, not a performance ranking. Match model weights, resolution, steps, software and timing scope before comparing. Playback FPS describes the output video.

SourceModelGPUsOutputMeasurements
View
ReportComfyUI		HunyuanVideo 1.5 720p I2VFP16Tested weights ↗Image → videoRadeon AI PRO R97001 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Linux (Fedora toolbox)
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2026-01-02
Full record →
1280 × 720≈ 5.04 s clip · Batch 1121 frames24 FPS playback4 stepsBatch 1
809.081 sGeneration time · reported
Whole workflow · Cold
View
ReportComfyUI		HunyuanVideo 1.5 480p CFG-distilled + 4-step LoRAFP8 scaledTested weights ↗Text → videoRadeon RX 9070 XT1 GPU
Configuration
Engine
ComfyUI 0.35.0
Backend
ROCm / HIP
OS
Windows 11
Parallelization
Single GPU
Memory
16 GB per GPU
Reported
2026-09-11
Full record →
848 × 480Frame count not reported4 stepsBatch not reported
252 sGeneration time · reported
Whole workflow · Timing details missing
View
ReportComfyUI		HunyuanVideo 1.5 720p I2VFP16Tested weights ↗Image → videoRadeon AI PRO R97001 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Linux (Fedora toolbox)
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2026-01-02
Full record →
1280 × 720≈ 5.04 s clip · Batch 1121 frames24 FPS playback4 stepsBatch 1
795.61 sGeneration time · reported
Whole workflow · Warm
View
ReportComfyUI		HunyuanVideo 1.5 720p I2VFP16Tested weights ↗Image → videoRadeon AI PRO R97001 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Linux (Fedora toolbox)
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2026-01-02
Full record →
1280 × 720≈ 5.04 s clip · Batch 1121 frames24 FPS playback4 stepsBatch 1
744.13 sGeneration time · reported
Whole workflow · Cold
View
ReportComfyUI		HunyuanVideo 1.5 720p I2VFP16Tested weights ↗Image → videoRadeon AI PRO R97001 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Linux (Fedora toolbox)
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2026-01-02
Full record →
1280 × 720≈ 5.04 s clip · Batch 1121 frames24 FPS playback4 stepsBatch 1
741.171 sGeneration time · reported
Whole workflow · Warm
View
ReportComfyUI		HunyuanVideo 1.5 720p T2VFP16Tested weights ↗Text → videoRadeon AI PRO R97001 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Linux (Fedora toolbox)
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2026-01-02
Full record →
1280 × 720≈ 5.04 s clip · Batch 1121 frames24 FPS playback4 stepsBatch 1
726.352 sGeneration time · reported
Whole workflow · Cold
View
ReportComfyUI		HunyuanVideo 1.5 720p T2VFP16Tested weights ↗Text → videoRadeon AI PRO R97001 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Linux (Fedora toolbox)
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2026-01-02
Full record →
1280 × 720≈ 5.04 s clip · Batch 1121 frames24 FPS playback4 stepsBatch 1
704.476 sGeneration time · reported
Whole workflow · Warm
View
ReportComfyUI		HunyuanVideo 1.5 720p T2VFP16Tested weights ↗Text → videoRadeon AI PRO R97001 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Linux (Fedora toolbox)
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2026-01-02
Full record →
1280 × 720≈ 5.04 s clip · Batch 1121 frames24 FPS playback4 stepsBatch 1
775.539 sGeneration time · reported
Whole workflow · Cold
View
ReportComfyUI		HunyuanVideo 1.5 720p T2VFP16Tested weights ↗Text → videoRadeon AI PRO R97001 GPU
Configuration
Engine
ComfyUI
Backend
ROCm / HIP
OS
Linux (Fedora toolbox)
Parallelization
Single GPU
Memory
32 GB per GPU
Reported
2026-01-02
Full record →
1280 × 720≈ 5.04 s clip · Batch 1121 frames24 FPS playback4 stepsBatch 1
743.797 sGeneration time · reported
Whole workflow · Warm
Explore all 9 configurations →

All video benchmarks · Methodology and source review