Acly/krita-ai-diffusion v1.53.0

Version 1.53.0

on GitHub

Download krita_ai_diffusion-1.53.0.zip

For Krita 5 (recommended: Krita 5.3.2.1)

Anima Segmentation Control

Segmentation control layer is now supported for Anima (PR by @Sen-sou).

Instructions:

1. Download the model and put it into models/controlnet
2. Create a Control Layer and select Segmentation mode
3. (Optional) Create a segmentation image from your existing Regions with the T button
4. Generate

Upgrades and Removals

• Upgraded managed server to CUDA 13, PyTorch 2.13 and latest ComfyUI
• Now supports int8 / int4 / ConvRot models #2553
• Removed Nunchaku support
• Removed insightface (used by SD1.5/SDXL Face-ID) from managed server install

If you were using the Nunchaku variants of Flux 1, Flux 1 Kontext, Qwen or Z-Image you will have to redownload alternative versions of these models. See models or use the Managed Server installation.

Cloud Changes

As an image generation service, Interstice.cloud complies with EU AI Act Transparency laws.

• Images saved from the history now contain a metadata tag to identify them as AI generated
• Images contain an invisible watermark with a fixed tag that links them to the service (users from EU only)

This does not affect local use!

Other Changes

• Fixed image history displaying timestamps in UTC instead of local timezone #2551
• New-lines are now preserved when importing prompts from PNG metadata (by @amiiari)
• Warn when there are duplicate parameter names in a custom workflow #2581