mirror of https://github.com/vladmandic/automatic
lint wiki
Signed-off-by: Vladimir Mandic <mandic00@live.com>master
parent
b53aab22fd
commit
8d63a0f046
2
Home.md
2
Home.md
|
|
@ -50,6 +50,7 @@ Additionally, you can either download your own models or use built-in [CivitAI](
|
|||
Some models may require additional access checks before they can be used: [Gated access](Gated.md)
|
||||
Learn how to optimize your environemnt: [Performance tuning](Performance-Tuning.md)
|
||||
Learn how you can manage your resources better:
|
||||
|
||||
- [Memory offloading](Offload.md)
|
||||
- [Model Quantization](Quantization.md)
|
||||
- [Model Compression](NNCF-Compression.md)
|
||||
|
|
@ -67,6 +68,7 @@ If you want to use SD.Next via API or via CLI,
|
|||
check out [tools examples](CLI-Tools.md)
|
||||
|
||||
If you want to understand more how Stable Diffusion works
|
||||
|
||||
- [Diffusion Pipeline: How it Works](SD-Pipeline-How-it-Works.md)
|
||||
- [List of Training Methods](SD-Training-Methods.md)
|
||||
|
||||
|
|
|
|||
3
SD3.md
3
SD3.md
|
|
@ -1,6 +1,7 @@
|
|||
# [Stable Diffusion 3.x](https://stability.ai/news/stable-diffusion-3-medium)
|
||||
|
||||
StabilityAI's Stable Diffusion 3 family consists of:
|
||||
|
||||
- [Stable Diffusion 3.0 Medium](https://huggingface.co/stabilityai/stable-diffusion-3-medium-diffusers)
|
||||
- [Stable Diffusion 3.5 Medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium-diffusers)
|
||||
- [Stable Diffusion 3.5 Large](https://huggingface.co/stabilityai/stable-diffusion-3.5-large)
|
||||
|
|
@ -31,6 +32,7 @@ StabilityAI's Stable Diffusion 3 family consists of:
|
|||
## Components
|
||||
|
||||
**SD3.x** model consists of:
|
||||
|
||||
- Unet/Transformer: MMDiT
|
||||
- Text encoder 1: [CLIP-ViT/L](https://huggingface.co/openai/clip-vit-large-patch14),
|
||||
- Text encoder 2: [OpenCLIP-ViT/G](https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k),
|
||||
|
|
@ -81,6 +83,7 @@ Since text encoders and VAE are same between all FLUX.1 models, *using all-in-on
|
|||
Unet/Transformer component is a typical model fine-tune and is around 11GB in size
|
||||
|
||||
To load a Unet/Transformer safetensors file:
|
||||
|
||||
1. Download `safetensors` or `gguf` file from desired source and place it in `models/UNET` folder
|
||||
2. Load model as usual and then
|
||||
3. Replace transformer with one in desired safetensors file using:
|
||||
|
|
|
|||
|
|
@ -1,3 +1,3 @@
|
|||
## Nvidia Graphics Card Note
|
||||
# Nvidia Graphics Card Note
|
||||
|
||||
You will likely want to follow [Nvidia's instructions to disable System Memory Fallback for Stable Diffusion](https://nvidia.custhelp.com/app/answers/detail/a_id/5490) on the newest drivers, which you should be using.
|
||||
|
|
|
|||
Loading…
Reference in New Issue