SD.Next vs Tensor.Art

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.

Tensor.Art has no write-up on Specifiction yet; its figures are above.