FidelityFx Super Resolution
FidelityFX Super Resolution (FSR) is AMD's open-source spatial upscaling technology designed to boost performance in real-time rendering applications, particularly video games.
Key Highlights
Hardware Agnostic Approach
Works on any supported GPU including AMD, NVIDIA and Intel, providing broad compatibility without requiring dedicated AI hardware
Temporal Upscaling (FSR 2.0)
Advanced temporal upscaling that accumulates information from multiple frames using motion vectors, depth buffers and historical frame data
Frame Generation Technology (FSR 3.0)
Offers frame generation capability that doubles the perceived frame rate by creating new interpolated frames between rendered frames
Wide Game Compatibility
Broad ecosystem support integrated into hundreds of game titles and major game engines like Unreal Engine and Unity
About
FidelityFX Super Resolution (FSR) is AMD's open-source upscaling technology designed primarily for real-time applications such as video games. First released in 2021, FSR bridges the gap between low-resolution frame rendering and high-resolution display output, significantly boosting gaming performance while minimizing visual quality trade-offs. It embodies AMD's commitment to an open platform approach that benefits all gamers regardless of their hardware vendor, and its hardware-agnostic philosophy has been setting industry direction.
The technical evolution of FSR spans multiple generations, with each generation introducing significant innovations. FSR 1.0 employed a spatial upscaling approach that analyzes a single frame and applies advanced Lanczos-based filtering combined with edge enhancement algorithms for improved visual clarity. FSR 2.0 introduced a fundamental architectural shift to temporal upscaling, leveraging motion vectors and information from previous frames to achieve substantially higher quality results comparable to native resolution rendering. FSR 3.0 added frame generation technology, using optical flow-based intermediate frame synthesis to dramatically increase perceived FPS beyond what the GPU can natively render. Each generation has progressively improved the visual quality and performance balance, elevating the overall gaming experience.
Platform independence is one of FSR's most defining characteristics and the primary advantage that distinguishes it from competing solutions. Unlike NVIDIA's DLSS, which requires dedicated Tensor Cores available only on RTX hardware, FSR operates without specialized hardware requirements and runs across NVIDIA, AMD, and Intel GPUs, including integrated graphics solutions found in budget systems and laptops. This broad compatibility enables game developers to reach their entire player base with a single implementation effort. FSR supports DirectX 11, DirectX 12, and Vulkan graphics APIs, and is widely deployed on console platforms including Xbox and PlayStation, ensuring comprehensive cross-platform coverage. It also plays a critical role on portable gaming devices.
Industry adoption within the gaming ecosystem has been exceptionally widespread and continues to grow with each new title release. Hundreds of AAA and independent titles offer FSR support across diverse genres. Major productions including God of War, Cyberpunk 2077, Forspoken, Starfield, and Hogwarts Legacy feature FSR integration as a standard option. Engine-level integrations with Unreal Engine and Unity enable developers to incorporate FSR into their projects with minimal implementation effort and rapid deployment. On portable gaming devices such as the Steam Deck, FSR has become a critical technology for achieving playable frame rates within limited GPU power budgets, fundamentally transforming the mobile gaming experience.
Quality modes include Ultra Quality, Quality, Balanced, Performance, and Ultra Performance tiers, each designed for different quality-performance trade-off preferences. Ultra Quality mode delivers near-native resolution image quality with modest performance gains, while Performance mode provides up to 2x performance improvement for demanding titles. Ultra Performance mode offers dramatic performance gains even at 4K resolution, though with more noticeable visual quality trade-offs. Users can select the most appropriate mode based on their hardware capabilities, display resolution, and personal quality-performance preferences to achieve an optimal gaming experience.
FSR is released as open source under the MIT license through AMD's GPUOpen platform, encouraging transparent collaboration and innovation. This open approach enables both game developers and researchers to inspect, modify, and adapt the technology for their specific needs, accelerating the pace of innovation across the industry. AMD's continued investment in the FSR ecosystem pushes quality and performance boundaries with each new generation, maintaining its position as a leading platform for real-time image upscaling technology. FSR is widely recognized as one of the foundational technologies shaping the future of the gaming industry.
Use Cases
Performance-Boosted Gaming
Maintaining visual quality while increasing frame rates by rendering at lower internal resolution
High Resolution on Older GPUs
Providing 4K or high-resolution gaming experience on mid-range or older GPUs
Game Engine Integration
Game developers adding upscaling technology to their Unreal Engine and Unity projects
Portable Device Optimization
Optimizing the balance between performance and visual quality on Steam Deck and other portable gaming devices
Pros & Cons
Pros
- AMD's open-source gaming upscaling technology — vendor agnostic
- Works on both AMD and NVIDIA GPUs
- Frame generation support with FSR 3 — FPS boost
- Easy integration into game engines — Unreal and Unity support
- No license fee — free to use
Cons
- Falls behind NVIDIA DLSS in visual quality
- Temporal instability — ghosting and shimmer artifacts
- Not AI-based (until FSR 2) — traditional spatial upscaling
- Noticeable quality loss in performance mode
Technical Details
Parameters
N/A
Architecture
Spatial upscaling (FSR 1) + Temporal upscaling with optical flow (FSR 2/3)
Training Data
N/A (algorithmic approach, not ML-trained)
License
MIT
Features
- Temporal Upscaling (FSR 2.0/3.0)
- Frame Generation (FSR 3.0)
- Cross-Platform GPU Support
- Open Source Implementation
- Game Engine Integration (Unreal/Unity)
- Multiple Quality Presets
Benchmark Results
| Metric | Value | Compared To | Source |
|---|---|---|---|
| Performans Artışı (Ultra Quality) | ~1.3x FPS | DLSS Ultra Quality: ~1.3x | AMD GPUOpen Documentation |
| Performans Artışı (Performance) | ~2.0x FPS | DLSS Performance: ~2.0x | AMD GPUOpen Documentation |
| Desteklenen GPU | Vendor-agnostic (AMD, NVIDIA, Intel) | DLSS: yalnızca NVIDIA RTX | AMD GPUOpen |
| Upscale Oranları | 1.3x, 1.5x, 1.7x, 2.0x | — | AMD GPUOpen Documentation |
Frequently Asked Questions
Related Models
CodeFormer
Evaluate CodeFormer for a permitted portrait restoration: compare fidelity settings, inspect face changes and recomposition, and check the non-commercial S-Lab license.
Real-ESRGAN
Real-ESRGAN is an open-source image upscaling and restoration model developed by Xintao Wang and collaborators at Tencent ARC Lab that enhances low-resolution, degraded, or compressed images to high-resolution outputs with remarkable detail recovery. Released in 2021 under the BSD license, Real-ESRGAN builds on the original ESRGAN architecture by introducing a high-order degradation modeling approach that simulates the complex, unpredictable quality loss found in real-world images, including compression artifacts, noise, blur, and downsampling. The model uses a U-Net architecture with Residual-in-Residual Dense Blocks as its generator network, trained with a combination of perceptual loss, GAN loss, and pixel loss to produce sharp, natural-looking upscaled results. Real-ESRGAN supports upscaling factors of 2x, 4x, and higher, and includes specialized model variants for anime and illustration content alongside the general-purpose photographic model. The model handles real-world degradations far better than its predecessor ESRGAN, which was trained only on synthetic degradation patterns. Real-ESRGAN has become one of the most widely deployed AI upscaling solutions, integrated into numerous applications including desktop tools, web services, mobile apps, and professional image editing workflows. The model runs efficiently on both CPU and GPU, with the lighter RealESRGAN-x4plus-anime variant optimized for consumer hardware. As a fully open-source project available on GitHub with pre-trained weights, it serves as the backbone for popular tools like Upscayl and various ComfyUI nodes. Real-ESRGAN is essential for photographers, content creators, game developers, and anyone who needs to enhance image resolution while preserving natural appearance and adding realistic detail.
StableSR
StableSR is an innovative super-resolution model developed by Jianyi Wang and collaborators that leverages the generative prior of a pre-trained Stable Diffusion model for high-quality image upscaling with realistic detail synthesis. Released in 2023 under the Apache 2.0 license, StableSR represents one of the first successful applications of diffusion-based generative models to the image super-resolution task. The model introduces a time-aware encoder that injects information from the low-resolution input image into the Stable Diffusion denoising process at each timestep, along with a controllable feature wrapping module that balances between fidelity to the original image and the richness of generated details. This architecture enables StableSR to produce upscaled images with remarkably realistic textures and fine details that go beyond what traditional regression-based super-resolution methods can achieve. The controllable feature wrapping allows users to adjust the strength of generative enhancement, providing a spectrum from conservative restoration that closely follows the input to aggressive enhancement that adds more synthesized detail. StableSR handles diverse image types including photographs, artwork, screenshots, and text-containing images, with particular strength in restoring natural textures like skin, hair, fabric, and foliage. The model is fully open source with code and pre-trained weights available on GitHub and is compatible with existing Stable Diffusion infrastructure. StableSR is valuable for photographers restoring low-resolution images, digital artists upscaling reference material, and content creators who need high-resolution outputs from limited source imagery. Its diffusion-based approach has influenced subsequent research in generative super-resolution methods.
SUPIR
Evaluate SUPIR restoration with controlled Q/F and caption comparisons, inspect invented detail, and clarify checkpoint permissions before a trial.
Quick Info
Spatial upscaling (FSR 1) + Temporal upscaling with optical flow (FSR 2/3)