GPU Requirements
VRAM requirements, supported GPU architectures, driver compatibility, and platform-specific GPU notes.
Recaster uses GPU acceleration for face swapping, enhancement, training, and video upscaling. While CPU processing is supported as a fallback, a dedicated NVIDIA GPU is strongly recommended for reasonable performance.
VRAM by Operation
The table below shows the approximate GPU memory (VRAM) required for each operation. These are estimates and may vary depending on input resolution and model settings.
| Operation | Minimum VRAM | Recommended VRAM | Notes |
|---|---|---|---|
| Face Swapping | 2 GB | 4 GB | InSwapper runs well on 2 GB; Ghost benefits from 4 GB |
| Face Enhancement | 2 GB | 4 GB | GPEN-2048 may need 6 GB at full resolution |
| Training (Quick96) | 4 GB | 6 GB | Smaller architecture, faster iterations |
| Training (SAEHD) | 6 GB | 8-12 GB | Higher dimensions require more VRAM |
| Training (AMP) | 6 GB | 8-12 GB | Similar to SAEHD requirements |
| Training (XSeg) | 4 GB | 6 GB | Mask training is less VRAM-intensive |
| Video Upscaling (2x) | 2 GB | 4 GB | Tile-based processing limits VRAM usage |
| Video Upscaling (4x/8x) | 2 GB | 4-6 GB | Multi-pass 2x uses same VRAM as single 2x |
Studio Tier Cloud GPUs
Driver Requirements
Recaster requires compatible NVIDIA drivers for GPU acceleration. Keep your drivers updated to the latest stable version for best compatibility.
NVIDIA CUDA Drivers
- NVIDIA driver version 535+ recommended
- CUDA 11.8 or 12.x supported
- Download from
nvidia.com/drivers
cuDNN (Remote Instances)
Remote training and processing instances require cuDNN 9 for ONNX Runtime GPU acceleration. This is automatically installed during provisioning, but can be manually installed if needed:
pip install nvidia-cudnn-cu12==9.1.0.70ONNX Runtime Compatibility
Recaster uses ONNX Runtime for model inference. Specific version pinning is required for reliable operation.
Version Pinning Required
| Package | Required Version | Notes |
|---|---|---|
| onnxruntime-gpu | 1.19.2 | NOT 1.23+ (compatibility issues) |
| NumPy | <2.0.0 | e.g. 1.26.4 (NumPy 2.0 breaks ONNX Runtime) |
| OpenCV | 4.5 - 4.10 | Use opencv-python, not opencv-python-headless |
If you encounter version conflicts on a remote instance, use the following commands to force correct versions:
pip install --force-reinstall onnxruntime-gpu==1.19.2
pip install --force-reinstall "numpy>=1.23.0,<2.0.0"
pip uninstall -y opencv-python-headless
pip install --no-deps "opencv-python>=4.5.0,<4.11.0"RTX 5000 Series (Blackwell)
RTX 5000 Series Limitations
Recaster shows a warning dialog on startup when an RTX 5000 series GPU is detected. The following workarounds are available:
- Remote Training (Recommended) — Use Studio tier cloud GPUs via Vast.ai. Works immediately with no local GPU constraints.
- WSL2 — Use Windows Subsystem for Linux with a community fork that supports Blackwell GPUs.
- Quick Recast and Upscaling — ONNX Runtime-based operations (face swapping, enhancement, upscaling) may work with RTX 5000 GPUs since ONNX Runtime updates CUDA support more frequently than TensorFlow.
Dismissing the Warning
gpu_compatibility_warning_dismissed: true in your settings file.macOS GPU Support
macOS does not support NVIDIA CUDA. GPU acceleration on Mac uses Apple's CoreML framework where available, with automatic fallback to CPU for unsupported operations.
| Operation | macOS Support | Notes |
|---|---|---|
| Real-ESRGAN | CoreML Accelerated | 10-20 FPS, recommended for Mac users |
| SwinIR | CPU Fallback | 2-5 FPS on CPU. CoreML does not support SwinIR dynamic shapes. |
| Face Swapping | Supported | ONNX Runtime CPU provider, adequate for most use cases |
| DFL Training | Limited | CPU only, very slow. Use remote training for practical results. |
Best Practice for Mac Users
Supported GPU Families
The following NVIDIA GPU families are tested and supported for local processing:
- RTX 40 Series — Full support. Best local performance.
- RTX 30 Series — Full support. Excellent performance.
- RTX 20 Series — Full support. Good performance.
- GTX 16 Series — Supported. Limited VRAM may restrict training.
- GTX 10 Series — Basic support. Face swapping works, training may be slow.
- RTX 50 Series — Partial support. See RTX 5000 section above.
AMD and Intel GPUs
Was this page helpful?