Recraft vs SD.Next
Recraft
recraft.aiSD.Next
github.comSide by side
| Figure | Recraft | SD.Next |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | Yes |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | — | Yes |
| iOS | Yes | — |
| Android | Yes | — |
| API | Yes | Yes |
| Self-hosted | — | Yes |
| Plans published | 9 | 1 |
| Spec score · AI image generators | 9.5 (#1) | 8.9 (#13) |
| API access | Yes | Yes |
| Image editing | Available editing operations include image-to-image changes, inpainting, outpainting, erasing regions, background removal and background replacement. | Yes |
| Output formats | SVG,PNG,JPG,PDF,TIFF,Lottie | PNG,JPG |
| Reference images | Yes | Yes |
| Text-to-image | Yes | Yes |
Plans
Recraft
- FreeFree
- Pro 2kPrice not published
- Pro 4kPrice not published
- Pro 8kPrice not published
- FreeFree
- API V4.1 Flash$0.01, paid once
- Basic$12 a month
- Teams$18 a month
- Pro$20 a month
In their own words
Recraft
Recraft provides text-to-image generation, reference image support and image editing, with output in SVG, PNG, JPG, PDF, TIFF and Lottie formats. API access is available, and API is the listed platform. Its free plan includes 30 daily credits. Monthly AI credits are listed as 1,000 credits per month, alongside the plan-specific credit amounts. Commercial use is limited. Recraft was founded in 2022 and is headquartered in London, United Kingdom. The free plan offers a way to use the product without a listed subscription price, while the named tiers specify progressively larger credit totals. The combination of image generation, editing, references and multiple export formats may be relevant to people creating or modifying visual assets, including those who need vector and raster outputs.
SD.Next
SD.Next is an open-source server application and web interface for generating, editing, captioning, upscaling and processing AI images and videos. Workflows include text-to-image, image-to-image, text-to-video, image-to-video, inpainting and outpainting, with PNG and JPG output. The project supports dozens of models and can automatically download selected reference models. Guidance features include LoRA, ControlNet, IPAdapters and Prompt Enhance. Image processing tools cover captioning, tagging, upscaling, interpolation, colorization, filtering and color correction. SDNQ quantization is described as reducing VRAM use by up to 4x; Balanced Offload balances CPU and GPU memory for larger models on limited hardware. Listed hardware options include CUDA, ROCm, ZLUDA, Intel IPEX XPU, OpenVINO, DirectML, Apple M1/M2 MPS, ONNX/Olive and CPU-only execution. SD.Next runs on Linux, macOS and Windows, and provides API access. The project describes desktop and mobile interfaces and localization in about 15 languages. Its security policy says it does not send or share data externally, track user or system data, store inputs or results, or use analytics services. The repository identifies Apache-2.0 as its license.