Krita AI DiffusionAI tool

Build and run local node-based image generation workflows.

Local inference has no required subscription, software purchase or paid model API. You supply compatible hardware, electricity, storage and initial downloads. SDXL weights have a separate Open RAIL++ license with use restrictions; software being open source does not make every model unrestricted. Optional cloud services, partner/API nodes and rented GPUs cost separately. Use a local SDXL workflow, not an API-node template. The core and desktop wrapper have different open-source licenses; cloud hosting is a separate paid edition.

Generate images locally through a prompt-focused SDXL interface.

Local inference has no required subscription, software purchase or paid model API. You supply compatible hardware, electricity, storage and initial downloads. SDXL weights have a separate Open RAIL++ license with use restrictions; software being open source does not make every model unrestricted. Optional cloud services, partner/API nodes and rented GPUs cost separately. Limited long-term support with bug fixes only; the observed default-branch commit is September 2025. Do not describe it as an actively developed current-model platform. Model checkpoints retain separate terms.

Invoke CommunityAI

Local AI Image Generators

Generate and edit images on a local canvas with downloaded diffusion models.

Local inference has no required subscription, software purchase or paid model API. You supply compatible hardware, electricity, storage and initial downloads. SDXL weights have a separate Open RAIL++ license with use restrictions; software being open source does not make every model unrestricted. Optional cloud services, partner/API nodes and rented GPUs cost separately. The Community software is distinct from hosted/commercial products. This selection covers local image generation, not proprietary paid model access.

SD.NextProduct logo · See the interface on the official website

SD.NextAI

Local AI Image Generators

Run a local web interface for image generation, refinement and processing.

Local inference has no required subscription, software purchase or paid model API. You supply compatible hardware, electricity, storage and initial downloads. SDXL weights have a separate Open RAIL++ license with use restrictions; software being open source does not make every model unrestricted. Optional cloud services, partner/API nodes and rented GPUs cost separately. This qualifies local image generation. Supported paid API models do not become free because the interface is Apache-licensed.