https://github.com/avaray/stable-diffusion-templates
A collection of Stable Diffusion Templates that will allow you to use best UIs with the best checkpoints and significantly reduce the time needed to get started.
https://github.com/avaray/stable-diffusion-templates
ai-dock auto1111 automatic-1111 automatic1111 generative-ai pdxl pony-diffusion ponydiffusion runpod sdxl stable-diffusion stable-diffusion-webui stablediffusion templates vast-ai vastai
Last synced: 6 months ago
JSON representation
A collection of Stable Diffusion Templates that will allow you to use best UIs with the best checkpoints and significantly reduce the time needed to get started.
- Host: GitHub
- URL: https://github.com/avaray/stable-diffusion-templates
- Owner: Avaray
- License: mit
- Created: 2024-08-03T19:16:37.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-03T13:20:04.000Z (7 months ago)
- Last Synced: 2025-04-14T12:13:53.127Z (6 months ago)
- Topics: ai-dock, auto1111, automatic-1111, automatic1111, generative-ai, pdxl, pony-diffusion, ponydiffusion, runpod, sdxl, stable-diffusion, stable-diffusion-webui, stablediffusion, templates, vast-ai, vastai
- Language: Shell
- Homepage: https://dav.one/templates
- Size: 322 KB
- Stars: 5
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- Funding: funding.yml
- License: LICENSE
Awesome Lists containing this project
README
# 🗃 Collection of Stable Diffusion Templates
This is curated collection of templates for [Vast.ai](https://cloud.vast.ai/create/?ref_id=62878) and [Runpod.io](https://runpod.io/console/deploy?ref=gzvzzzv9) services.
Their main purpose is to simplify the process of getting started with Stable Diffusion.
These templates gives ready to use [Automatic1111 WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) thanks to [AI-Dock](https://github.com/ai-dock/stable-diffusion-webui).
Plus they have some nice Lora's and useful Extensions preinstalled.
### Start generating graphics in minutes with just few clicks 😎
# 🦓 SDXL
Templates with checkpoints based on [Stable Diffusion XL](https://en.wikipedia.org/wiki/Stable_Diffusion).
| Rating | Checkpoint
Name | Version | Vast.ai | Runpod.io |
| :--------------: | :----------------: | :-----: | :-----: | :-------: |
| 🔥 | [RealVis](https://civitai.com/models/139562?modelVersionId=344487) | `V4` | 
| 
|
| 🔥 | [RealVis](https://civitai.com/models/139562?modelVersionId=789646) | `V5` | | |
| - | [ZavyChroma](https://civitai.com/models/119229?modelVersionId=916744) | `V10` | todo | todo |
| 🔥 | [ZavyChroma](https://civitai.com/models/119229?modelVersionId=641087) | `V9` | | |
| 👍 | [ZavyChroma](https://civitai.com/models/119229?modelVersionId=490254) | `V7` | | |
| 🔥 | [WildCardX](https://civitai.com/models/239561?modelVersionId=308455) | `V4` | | |
| 🔥 | [CHINOOK](https://civitai.com/models/400589?modelVersionId=495482) | `V1` | | |
| 👍 | [LEOSAM's HelloWorld](https://civitai.com/models/400589?modelVersionId=495482) | `V7` | | |
| - | [Juggernaut](https://civitai.com/models/133005?modelVersionId=782002) | `V11` | | |
| 👍 | [Juggernaut](https://civitai.com/models/133005?modelVersionId=456194) | `V10` | | |
| 👍 | [DreamShaper](https://civitai.com/models/112902?modelVersionId=126688) | `V2a` | | |
| - | [Copax TimeLess](https://civitai.com/models/118111?modelVersionId=445348) | `V12` | | |
| - | [epiCRealism](https://civitai.com/models/277058?modelVersionId=931522) | `V9-UnFlux` | todo | todo |
| 👍 | [epiCRealism](https://civitai.com/models/277058?modelVersionId=646523) | `V8` | | |
| 👍 | [Halcyon](https://civitai.com/models/299933?modelVersionId=655762) | `V1.8` | | |
| - | [PhotoPedia](https://civitai.com/models/189109?modelVersionId=259323) | `V4.5` | | |
| 👍 | [AlbedoBase](https://civitai.com/models/140737?modelVersionId=892880) | `V3-mini` | todo | todo |
# 🦄 PDXL
Templates with checkpoints based on Pony Diffusion XL.
| Rating | Checkpoint
Name | Version | Vast.ai | Runpod.io |
| :--------------: | :----------------: | :-----: | :-----: | :-------: |
| 🔥 | [GODDESS of Realism](https://civitai.com/models/212737?modelVersionId=573082) | `V1` | | |
| 🔥 | [Pony Diffusion](https://civitai.com/models/257749?modelVersionId=290640) | `V6` | | |
| 👍 | [AutismMix](https://civitai.com/models/288584?modelVersionId=324619) | `V1` | | |
| - | [fennfoto](https://civitai.com/models/503537?modelVersionId=702110) | `V4` | | |
| 👍 | [fennfoto](https://civitai.com/models/503537?modelVersionId=676770) | `V3` | | |
# 🙊 What is [Vast.ai](https://cloud.vast.ai/create/?ref_id=62878) and [Runpod.io](https://runpod.io/console/deploy?ref=gzvzzzv9) ?
These are services that gives you access to powerful [GPUs](https://en.wikipedia.org/wiki/Graphics_processing_unit) like [RTX4090](https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/rtx-4090/) at low cost.
They let you run [Docker images](https://docs.docker.com/guides/docker-overview/#what-can-i-use-docker-for) on their servers.
If you can't afford to buy a powerful Graphics Card (that is mandatory in graphics generation), these services are for you. In my opinion, services like these are the best way to get started with Stable Diffusion when you have weak graphics card and you don't have money to buy a powerful one. Btw. You can read [my old article](https://dav.one/the-ways-and-costs-of-generating-graphics-using-stable-diffusion) about _"the ways and costs of generating graphics"_.
These two services offer a lot of different machines with different hardware. There are also community machines that are cheaper. Both services have machine browsers where you can find the best machine for your needs. Currently renting community machine with RTX4090 on [Vast.ai](https://cloud.vast.ai/create/?ref_id=62878) costs about $0.3 per hour. On [Runpod.io](https://runpod.io/console/deploy?ref=gzvzzzv9) it's a little bit more expensive. Prices are generally lower on weekends. Global economy and events influence the prices.
When you are registered on these services and logged in, you can use the links above to rent a machine with selected template. **It's super easy.**
# 🙉 What is [AI-Dock](https://github.com/ai-dock/stable-diffusion-webui) and [Provisioning Script](https://github.com/ai-dock/base-image/wiki/4.0-Running-the-Image#provisioning-script) ?
[AI-Dock](https://github.com/ai-dock/stable-diffusion-webui) allows users to run _Stable Diffusion_ with latest version of [Automatic1111 WebUI](https://github.com/AUTOMATIC1111/stable-diffusion-webui) in a [Docker container](https://docs.docker.com/guides/docker-concepts/the-basics/what-is-a-container/). In my opinion the biggest advantage of this solution is that it starts quickly and you are able to connect to machine before all the checkpoints are downloaded. Because of that you can know at the beginning if docker image will work on machine you rented. Without AI-Dock you might waste few minutes waiting for checkpoints to download and then you will find out that something is wrong and you need to rent another machine. Except that AI-Dock comes with [Provisioning Script](https://github.com/ai-dock/base-image/wiki/4.0-Running-the-Image#provisioning-script), which is a script that installs all the necessary dependencies and downloads the checkpoints before starting the WebUI. So you don't need to do things manually.
Except [Automatic1111](https://github.com/AUTOMATIC1111/stable-diffusion-webui), AI-Dock supports also other popular WebUIs like [ComfyUI](https://github.com/comfyanonymous/ComfyUI), [InvokeAI](https://github.com/invoke-ai/InvokeAI) and [Foooocus](https://github.com/lllyasviel/Fooocus). But all templates in this repository are based on Auto1111 - because it's my favorite WebUI.
# 🙈 Provisioning scripts in my Templates
Provisioning scripts in this Collection are based on official [Provisioning Script](https://github.com/ai-dock/stable-diffusion-webui/blob/main/config/provisioning/default.sh).
In process of creating my provisioning scripts I'm replacing some parts of original script with my own stuff.
Currently it includes:
- Each script has just one specific checkpoint. Does not include stock checkpoints.
- Each script has some useful Lora's that will work with that checkpoint. Basically there are two lists of Lora's - one for checkpoints based on [SDXL](https://github.com/Avaray/stable-diffusion-templates?tab=readme-ov-file#-sdxl) and one for checkpoints based on [PDXL](https://github.com/Avaray/stable-diffusion-templates?tab=readme-ov-file#-pdxl).
- Each script has some useful Extensions. Basically the same for all scripts. Except `taggers`.
To see what is included in each script, you can check sripts in [scripts directory](https://github.com/Avaray/stable-diffusion-templates/tree/main/scripts).
In near future I will also add some useful Embeddings (Textual Inversions).
# 📋 TODO's
- [ ] Reorganize the file structure in the repository.
- [ ] Remove some Loras and categorize them.
- [ ] Add links to scripts in README file.
- [ ] Add Embeddings to templates.
- [ ] Add lists of Embeddings to README file.
- [ ] Add automatic tests.
- [ ] Add links to Lora models on CivitAI.
- [ ] Create Lite versions (without Loras).
- [ ] Find a way to automate the creation and modification of templates so that Playwright isn't needed.
# ♻️ FAQ
`Q` Will you add model X?
`A` Probably not. I'm adding only the good ones (in my opinion). If you think that some checkpoint should be included, please [open an discussion](https://github.com/Avaray/stable-diffusion-templates/discussions/new?category=ideas). But keep in mind that model must be battle tested on [CivitAI](https://civitai.com/models) or on another platform. Also it needs to be tested by me.
`Q` Will you add more Loras and Extensions?
`A` Maybe. I'm still looking for useful ones.
`Q` Will you add other services than Vast.ai and Runpod.io?
`A` Maybe. Currently I don't know any better or at least as good as current ones.