v0.10.0

Features

This release has been a long time coming and accumulated a lot of features along the way, but it needs to be released to make way for SDXL.

• add support for ControlNet
  • adds an additional pipeline that can be used with the img2img tab
  • adds input filters to modify the source image before running the diffusion model
• add highres mode
  • runs a txt2img stage followed by repeated upscaling and img2img
  • very similar method to SDXL and the high res/hires fix in other tools
  • available for most tabs, except the blend tab
• add support for LyCORIS networks
  • LoCON and LoHA
  • using the same lora:name:weight token as LoRA networks
  • contributions from @ForserX
• add support for wildcard files
  • using __file/name__ tokens
  • not shown in the web GUI yet
• add additional upscaling models
  • BSRGAN
  • SwinIR
• add metadata to images
  • saves the prompt and other parameters in the image EXIF data
  • compatible with Civitai and other Stable Diffusion UIs
  • you can load parameters from image files in the web GUI
• add dark mode to GUI
  • thanks to @bzlibby
• add parameter profiles to GUI
  • allows you to save and load parameters with a name or keyword
  • thanks to @xbenjii
• run inpainting at full resolution
  • when you are inpainting a small portion of a larger image, the inpainting model will only be run on that section, providing higher detail and reducing unwanted changes elsewhere
  • thanks to @HoopyFreud
• rewrite spiral tiling code to overlap better and handle non-square images
  • thanks to @HoopyFreud
• rewrite all pipelines to use chain stages
  • more consistent handling of cancellation and progress
  • better support for parsing and filtering prompt/source image
• add additional chain pipeline stages
  • linear blend between images
  • S3 source download
  • URL source download

ControlNet

An ONNX version of the ControlNet pipeline for SD v1 and v2 has been added. You can use it by selecting the ControlNet pipeline and using the img2img tab normally.

There are additional parameters for the ControlNet model and source image filter, which can be used to pre-process images into a pose or depth map or run edge detection.

Highres

The highres mode allows you to create much larger and more detailed images without increasing GPU memory usage, by running an initial txt2img stage followed by upscaling and img2img. The highres stages can be repeated more than once with a low strength, gradually increasing the amount of detail in the image while also upscaling it. This helps correct for any loss of detail that upscaling may introduce and can easily produce 6-8k backgrounds.

LyCORIS

The <lora:name:weight> tokens now support most LyCORIS networks as well, especially LoCON and LoHA. You should download the networks into the same models/lora folder as other LoRA networks.

Wildcards

You can now use wildcard files to add some variety to your prompts. This supports most .txt files and some .yaml wildcards. After extracting any archives, place the wildcard files into the models/wildcard folder and use them by surrounding the filename with two underscores, like __test-wildcards__ (omit the file extension).

Wildcards can be placed into sub-folders and can refer to each other and themselves. Each item will only be used once per prompt, so infinite recursion is not possible. The wildcards are selected based on the seed, so using the same seed will produce the same prompt.

You can find some wildcard collections at:

• https://github.com/adieyal/sd-dynamic-prompts/tree/main/collections
• https://github.com/mattjaybe/sd-wildcards
• and on Civitai: https://civitai.com/

Artifacts

• https://ssube.github.io/onnx-web/v0.10.0/index.html
• https://hub.docker.com/repository/docker/ssube/onnx-web-api
  • podman pull docker.io/ssube/onnx-web-api:v0.10.0-cpu-buster
  • podman pull docker.io/ssube/onnx-web-api:v0.10.0-cuda-ubuntu
  • podman pull docker.io/ssube/onnx-web-api:v0.10.0-rocm-ubuntu
• https://hub.docker.com/repository/docker/ssube/onnx-web-gui
  • podman pull docker.io/ssube/onnx-web-gui:v0.10.0-nginx-alpine
  • podman pull docker.io/ssube/onnx-web-gui:v0.10.0-nginx-bullseye
  • podman pull docker.io/ssube/onnx-web-gui:v0.10.0-node-alpine
  • podman pull docker.io/ssube/onnx-web-gui:v0.10.0-node-bullseye
• https://www.npmjs.com/package/@apextoaster/onnx-web
  • yarn add @apextoaster/onnx-web@0.10.0
• https://pypi.org/project/onnx-web/
  • pip install onnx-web==0.10.0

Release checklist: #368
Release milestone: https://github.com/ssube/onnx-web/milestone/10
Release pipeline: https://git.apextoaster.com/ssube/onnx-web/-/pipelines/53887

Footnote

Work has already started on v0.11, featuring support for SDXL and a way to provide additional prompts for XL and highres. Combining highres with XL provides a whole new level of detail.