|
|
--- |
|
|
license: other |
|
|
license_name: bespoke-lora-trained-license |
|
|
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Rent&allowDerivatives=True&allowDifferentLicense=False |
|
|
tags: |
|
|
- text-to-image |
|
|
- stable-diffusion |
|
|
- lora |
|
|
- diffusers |
|
|
- template:sd-lora |
|
|
- 3d |
|
|
- retro |
|
|
- nintendo |
|
|
- gaming |
|
|
- style |
|
|
- 1990s |
|
|
- artstyle |
|
|
- videogames |
|
|
- videogame |
|
|
- styles |
|
|
- n64 |
|
|
- nintendo 64 |
|
|
|
|
|
base_model: stabilityai/stable-diffusion-xl-base-1.0 |
|
|
instance_prompt: N64 artstyle |
|
|
widget: |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2174774.jpeg |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2174804.jpeg |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2173745.jpeg |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2173654.jpeg |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2174678.jpeg |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2173704.jpeg |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2173655.jpeg |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2174557.jpeg |
|
|
- text: ' ' |
|
|
output: |
|
|
url: >- |
|
|
2174522.jpeg |
|
|
|
|
|
--- |
|
|
|
|
|
# Doctor Diffusion's N64 XL LoRA - 218MB & 7MB Versions |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## Model description |
|
|
|
|
|
<p>Use <strong>N64 artstyle </strong>in prompt. <br /><br />The 100 epochs 218MB XL version I followed <a target="_blank" rel="ugc" href="https://civitai.com/articles/1771/how-to-create-near-perfect-character-and-style-loras-for-sdxl-10-important-update-19082023"><strong><span style="color:rgb(193, 194, 197)">AI_Characters's</span></strong></a> <a target="_blank" rel="ugc" href="https://civitai.com/articles/1771/how-to-create-near-perfect-character-and-style-loras-for-sdxl-10-important-update-19082023">guide on LoRA settings</a> but used a total of 106 images as well as my own artstyle regulation images. <br /><br />The smaller 20 epochs 7MB version was done with experimental settings. Its small size it why it call it a SDSX LoRA.<br /><br />Inspired partially by both <a target="_blank" rel="ugc" href="https://civitai.com/user/veryVANYA/models"><strong><span style="color:rgb(193, 194, 197)">veryVANYA's </span></strong></a><span style="color:rgb(193, 194, 197)">outstanding </span><a target="_blank" rel="ugc" href="https://civitai.com/models/129556/ps1-graphics-sdxl"><span style="color:rgb(193, 194, 197)">PS1 LoRA</span></a><span style="color:rgb(193, 194, 197)"> (you should download and try) and my 90's childhood.</span></p> |
|
|
|
|
|
## Trigger words |
|
|
You should use `N64 artstyle` to trigger the image generation. |
|
|
|
|
|
|
|
|
## Download model |
|
|
|
|
|
Weights for this model are available in Safetensors format. |
|
|
|
|
|
[Download](/DoctorDiffusion/doctor-diffusion-s-n64-xl-lora-218mb-7mb-versions/tree/main) them in the Files & versions tab. |
|
|
|
|
|
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) |
|
|
|
|
|
```py |
|
|
from diffusers import AutoPipelineForText2Image |
|
|
import torch |
|
|
|
|
|
pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to('cuda') |
|
|
pipeline.load_lora_weights('DoctorDiffusion/doctor-diffusion-s-n64-xl-lora-218mb-7mb-versions', weight_name='DD-N64-artstyle-XL-v1.safetensors') |
|
|
image = pipeline('`N64 artstyle`').images[0] |
|
|
``` |
|
|
|
|
|
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters) |
|
|
|
|
|
|
