Releases: Acly/krita-ai-diffusion
Releases · Acly/krita-ai-diffusion
Release list
Version 1.53.0
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:
- Download the model and put it into
models/controlnet - Create a Control Layer and select Segmentation mode
- (Optional) Create a segmentation image from your existing Regions with the
Tbutton - 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
Contributors
Sen-sou and amiiari
Assets 3
Version 1.52.1
Download krita_ai_diffusion-1.52.1.zip
For Krita 5 (recommended: Krita 5.3.2.1)
Changes
- Fixed plugin not connecting to the managed server after it was started #2548
Version 1.52.0
Download krita_ai_diffusion-1.52.0.zip
For Krita 5 (recommended: Krita 5.3.2.1)
Important
Because auto-update was broken in the previous version, please download and install this version manually.
Changes
- Basic support for Krea 2 model, see discussion (#2541 by @fukc-gihtub)
- Region support for Anima (#2480 by @Sen-sou)
- Fixed auto-updates installing to the wrong folder #2533
- Fixed model architecture not being set correctly from style in custom workflows (#2529 by @mtsmfm)
- Increased maximum prompt text box size #2538
- Use edit mode for expanding images with Flux Klein 9B #2518
Contributors
mtsmfm, Sen-sou, and fukc-gihtub
Assets 3
Version 1.51.1
Download krita_ai_diffusion-1.51.1.zip
For Krita 5 (recommended: Krita 5.3.1)
Changes
- Fixed managed installation on macOS #2505
- Fixed managed installation upgrade from old environments (Linux)
Version 1.51.0
Download krita_ai_diffusion-1.51.0.zip
For Krita 5 (recommended: Krita 5.3.1)
Control layers for Anima
Supported control modes:
- for official v1.0: Scribble, Line Art, Unblur
- for old preview models: Depth, Pose
Fill, Expand, etc. at full strength now requires the inpaint control model and gives much better results.
Please check the discussion for model downloads! PR by @Sen-sou
Other Changes
- Added ROCm as managed install option for supported AMD GPUs #76 #2315 #2493
- Fixed wrong assignments of
<layer:name>references in prompts - De-duplicate references to the same layer in more cases so they are only passed to the model once
- Fixed crash when a single-channel layer is used as input (eg. transparency mask) #2492
- Fixed the upscale strength slider being permanently disabled after selecting an edit model #2499
- Fixed issues when opening a document, especially with custom workflows #2479
- Changed color match functionality to detect when there is no color information outside the selection #2483
- Improved error message when trying to use reference layers in the prompt, but the model does not support them
- Improved file handling when come files are inaccessible (eg. access denied due to permissions)
Contributors
Sen-sou
Assets 3
Version 1.50.0
Download krita_ai_diffusion-1.50.0.zip
New Models (Preview)
Anima
- 2B parameter model for Anime and 2D, still being trained
- Supports tag based and natural language prompts
- Preview models can now be used for generation (#2450 by @FeepingCreature)
- See #2477 for downloads and more information
ERNIE Image
- 8B parameter model good for precise instructions and text
- Base and Turbo models can now be used for generation (#2459 by @eruanno123)
- See #2478 for downloads and more information
Other Changes
Contributors
FeepingCreature and eruanno123
Assets 3
Version 1.49.1
Download krita_ai_diffusion-1.49.1.zip
for Krita 5.2 or 5.3
Changes
- Fixed "refine" with less than 100% strength not working correctly for Flux 2 Klein #2392
- Use multiple-of-16 resolutions for internal resize to avoid artifacts at bottom/right borders #2436
- Custom workflows: Added a button to reset all parameters to default values #2402
- Fixed style not updating when switching between multiple documents that use different styles
- Fixed UI showing welcome state after opening a document instead of switching to image generation
- Fixed Flux 1 styles missing their checkpoint on non-CUDA installs
- Managed install now tries to install an older version of PyTorch for NVIDIA GTX 10xx #1871 #2396 #2426
- Changed the fixed seed widget to support larger numbers (up to 2^32) (by @LennyArchive)
- Fixed missing access token for custom ComfyUI authentication (by @sohaieb)
- Custom workflows: don't crop the preview image, allow workflows to return smaller or larger results #2418 #2419
- Custom workflows: fixed that some padding was still applied to selections masks even when "mask bounds"
- Assume SDXL-like checkpoints are Illustrious architecture when SDXL workload has not been installed to avoid warnings
- Refer to "workloads" on the connection screen in settings #2400
Contributors
sohaieb and LennyArchive
Assets 3
Version 1.49.0
Download krita_ai_diffusion-1.49.0.zip
Favourite Styles
When switching Styles, the most recent ones are now listed on top.
- Number of recent Styles can be configured in Interface settings (set to 0 to disable)
- Renamed some built-in styles to encourage their use over old/obsolete models
Prompt Hightlighting
- Special instructions in prompts are now highlighted
- Hex color codes are no longer treated as comments
Other Changes
- Added a button to toggle edit mode in the live workspace
- Flux 2 styles can now be linked as edit styles #2369
- Enabled "Scribble" control mode for Z-Image
- Custom graph parameters are now remembered for each individual workflow #2362
- Fixed selected custom graph now being restored when loading a document in some cases #2363
- Fixed animation frame batch generation with Flux 2 in edit mode #2372
- Disabled auto-exclusion of control and preview layers in custom graph live mode to avoid interruption #2376
- Fixed bad results with some models when using CFG with an empty negative prompt #2382
- Fixed spacing for Generate and Queue buttons on high-DPI displays
- Fixed issue with "Expand" selections when they were not overlapping with existing content
Version 1.48.0
Download krita_ai_diffusion-1.48.0.zip
Flux 2 Fill & Expand improvements
Improved behavior when using Fill or Expand with Flux 2 4B, especially without prompt.
| Original | Old (v1.47.0) |
|---|---|
 |
 |
| New (v1.48.0) | New + Color Match |
 |
 |
Color match
- Works for all models, but strongest effect on edit models
- Can be disabled in Diffusion settings
- Requires a selection. Matches colors outside of the selection area.
Note
External/custom ComfyUI installs
- Outpaint LoRA is used for Fill/Expand: download →
models/loras/flux-2-klein-4B-outpaint-lora.safetensors - Use "Generate (Custom)" to use regular inpainting (no edit, no LoRA)
- Remember to update comfyui-inpaint-nodes
Other Changes
- Added ControlNet support for Qwen image model by @krigeta #2332
- Fixed Lora widget showing incomplete list or displaying wrong text #2357
- Strength now fully applies to feather modifiers for selections [documentation]
- Fixed selection blend mask being too large when it connects with the borders of the canvas
- Custom workflows: Fixed regular/live sampling parameters passed to custom workflows #2341
- Custom workflows: Added a mask output to KritaCanvas custom node #2354
- Custom workflows: Sliders and number edit widgets now have more sensible step values #2342
- Fixed prompt metadata when using an empty prompt
- Bring back "Add Content" fill mode that was accidentaly removed in a prior version
- Added alternative Flux2 4B model download for non-CUDA managed install
- Deprecated DirectML support. It is still supported, but not recommended - AMD users are usually better off installing ComfyUI manually with ROCm support
- Added a button to collect diagnostics and system information, which can be copied into bug reports
- Removed Omni upscale models 3x/4x from required models list
- Fixed missing extension when creating a default style
Contributors
krigeta
Assets 3
Version 1.47.0
Download krita_ai_diffusion-1.47.0.zip
Flux 2 and Z-Image support
Flux 2 [klein] and Z-Image are now supported "officially", with automatic local installation and availability on cloud.
Left: generated with Z-Image | Right: series of edits with Flux 2 klein
Managed Install
Online Service [Interstice.cloud]
- Added Flux 2 klein
- Added Z-Image Turbo
- To be removed: Flux 1 schnell will no longer be available after 2026/03/01
- Plugin can now queue the next request already while it is receiving result images, allows faster batch generation
Other Changes
- Custom workflows: added new node "Krita Style & Prompt" by @leha-games #2276
- get prompt processing (style merge, loras and wildcards) in custom workflows [documentation]
- Limit selection blend (blur for alpha compositing) to outside of user selection #2299
- Fixed reference images for edit not added to batch generation #2300
- Fixed tiled upscale with Flux 2 (was not working in some cases because of tile size mismatch)
- Added edit toggle checkbox in custom inpaint menu #2307
- Fixed prompt weight adjustment (Ctrl+Up/Down) when prompt text contains non-ASCII characters (eg. emojis) #2306
- Fixed potential cause for assertion popup when opening a document #2298
- Improved match of "Qwen2.5-VL-7B" for Qwen-Image text encoder #2311
- Added "res multistep" sampler to built-in sampler options
- Mapped special inpaint modes (add/remove object, replace background) to edit instructions when using Flux 2
- Managed install: don't modify shell/environment when installing uv
- Fixed change of edit prompt not being saved to document
- Fixed resource ID for flux VAEs in models.json and download_models script
Contributors
leha-games