apextoaster
/
onnx-web
1
0
Fork 0
Code Actions

fix phrasing, add discord links to getting started guide

This commit is contained in:
Sean Sube 2023-12-17 16:43:38 -06:00
parent 9e734706f1
commit d643d12fd9
Signed by: ssube
GPG Key ID: 3EED7B957D362AF1
1 changed files with 15 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
docs/getting-started.md
View File

@ -23,6 +23,9 @@ This guide sets the stage for your onnx-web journey, offering a balance of techn
empower you in your AI art exploration. Let's embark on this creative venture together, where innovation meets technical empower you in your AI art exploration. Let's embark on this creative venture together, where innovation meets technical
precision. precision.
If you have any problems or questions that are not answered here, please [join the Discord
server](https://discord.gg/7CdQmutGuw) and ask.
## Contents ## Contents
- [Getting Started](#getting-started) - [Getting Started](#getting-started)
@ -110,7 +113,7 @@ For more details, please see [the server admin guide](./server-admin.md#containe
## Running ## Running
Running onnx-web is the gateway to unlocking the creative potential of Stable Diffusion in AI art. Whether you are a Running onnx-web is the gateway to unlocking the creative potential of Stable Diffusion in AI art. Whether you are a
novice or an experienced enthusiast, this section guides you through the process of installing onnx-web on your system. novice or an experienced enthusiast, this section guides you through the process of starting onnx-web on your system.
### Running the server ### Running the server
@ -131,12 +134,11 @@ realm of Stable Diffusion without compromise.
## Tabs ## Tabs
Understanding onnx-web's Core Features: onnx-web introduces a set of core features that form the backbone of your AI art onnx-web includes a set of core features that form the backbone of your AI art journey. The Stable Diffusion process,
journey. The Stable Diffusion process, capable of running on both AMD and Nvidia GPUs, powers the image generation capable of running on both AMD and Nvidia GPUs, powers the image generation pipeline. Explore the diverse tabs in the
pipeline. Explore the diverse tabs in the web UI, each offering unique functionalities such as text-based image web UI, each offering unique functionalities such as text-based image generation, upscaling, blending, and model
generation, upscaling, blending, and model management. Dive into the technical details of prompt syntax, model management. Dive into the technical details of prompt syntax, model conversions, and the intricacies of parameters,
conversions, and the intricacies of parameters, gaining a deeper understanding of how to fine-tune the AI art creation gaining a deeper understanding of how to fine-tune the AI art creation process.
process.
### Txt2img Tab ### Txt2img Tab
@ -149,7 +151,7 @@ For more details, please see [the user guide](./user-guide.md#txt2img-tab).
### Img2img Tab ### Img2img Tab
For image-based prompts, the img2img tab is the go-to interface within onnx-web. Beyond its fundamental image For image-based prompts, the img2img tab is the go-to interface within onnx-web. Beyond its fundamental image
generation capabilities, this tab introduces the ControlNet mode, empowering users with advanced control over the generation capabilities, this tab includes the ControlNet mode, empowering users with advanced control over the
generated images through an innovative feature set. generated images through an innovative feature set.
For more details, please see [the user guide](./user-guide.md#img2img-tab). For more details, please see [the user guide](./user-guide.md#img2img-tab).
@ -264,7 +266,7 @@ These parameters are unique to how onnx-web generates images.
images but also reduces VRAM usage. Notably, it doesn't exert a substantial impact on image quality, making it a images but also reduces VRAM usage. Notably, it doesn't exert a substantial impact on image quality, making it a
pragmatic choice for scenarios where resource efficiency is a priority. pragmatic choice for scenarios where resource efficiency is a priority.
- VAE tile size - VAE tile size
- Parallel to UNet, the VAE (Variational Autoencoder) introduces two additional parameters: VAE tile size and VAE - Parallel to UNet, the VAE (Variational Autoencoder) has two additional parameters: VAE tile size and VAE
overlap. These mirror the UNet tile size and UNet overlap parameters, applying specifically to the VAE when the overlap. These mirror the UNet tile size and UNet overlap parameters, applying specifically to the VAE when the
tiled VAE is active. Careful consideration of these parameters ensures effective utilization of onnx-web's tiled VAE is active. Careful consideration of these parameters ensures effective utilization of onnx-web's
capabilities while adapting to the unique requirements of your image generation tasks. capabilities while adapting to the unique requirements of your image generation tasks.
@ -372,7 +374,7 @@ from others, enabling collaborative exploration and knowledge exchange within th
user-friendly tool, onnx-web strives to enhance the customization and sharing aspects of image generation, providing user-friendly tool, onnx-web strives to enhance the customization and sharing aspects of image generation, providing
users with a flexible and collaborative experience. users with a flexible and collaborative experience.
TODO: link Discord profiles channel To find more profiles and share your own, [join the Discord server](https://discord.gg/7CdQmutGuw).
## Panorama pipeline ## Panorama pipeline
@ -415,14 +417,14 @@ For more details, please see [the user guide](./user-guide.md#reseed-tokens-regi
## Grid mode ## Grid mode
onnx-web introduces a powerful feature known as Grid Mode, designed to facilitate the efficient generation of multiple onnx-web includes a powerful feature known as Grid Mode, designed to facilitate the efficient generation of multiple
images with consistent parameters. Once enabled, Grid Mode allows users to select a parameter that varies across images with consistent parameters. Once enabled, Grid Mode allows users to select a parameter that varies across
columns and another for rows. Users then provide specific values for each column or row, and the images are generated columns and another for rows. Users then provide specific values for each column or row, and the images are generated
by combining the current parameters with the specified column and row values. by combining the current parameters with the specified column and row values.
In Grid Mode, selecting different parameters for columns and rows ensures diverse variations in the generated images. In Grid Mode, selecting different parameters for columns and rows ensures diverse variations in the generated images.
It's important to note that the same parameter cannot be chosen for both columns and rows unless the token replacement It's important to note that the same parameter cannot be chosen for both columns and rows unless the token replacement
option is activated. Token replacement introduces the keywords column and row within the prompt, allowing users to option is activated. Token replacement places the keywords column and row within the prompt, allowing users to
dynamically insert the column or row values into their prompts before image generation. dynamically insert the column or row values into their prompts before image generation.
While there isn't a strict limit on the number of values users can provide for each dimension (columns and rows), it's While there isn't a strict limit on the number of values users can provide for each dimension (columns and rows), it's
@ -446,7 +448,7 @@ facilitating nuanced and controlled variations in image generation.
## Memory optimizations ## Memory optimizations
onnx-web introduces optimizations tailored for users with limited memory resources. The system requirements are mostly onnx-web includes optimizations tailored for users with limited memory resources. The system requirements are mostly
based on how much memory you have: based on how much memory you have:
- minimum requirements - minimum requirements