|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
language: |
|
- en |
|
library_name: diffusers |
|
tags: |
|
- stable-diffusion |
|
- text-to-image |
|
--- |
|
|
|
|
|
# pony-diffusion-g5 - a new generation ~~of waifus~~ |
|
|
|
**UPDATE:** Plot twist I made a new version of this model which has much higher quality and is based on LoCon and with Mane 5 + Misty! [pony-diffusion-g5-lora](https://huggingface.co/GrieferPig/pony-diffusion-g5-lora) |
|
|
|
~~**UPDATE:** due to lots of poor results generated from the model and I will no longer update this model, please use [pony-diffusion-v4](https://huggingface.co/AstraliteHeart/pony-diffusion-v4) instead which is way better trust me they've got experts doing training stuff~~ |
|
|
|
pony-diffusion-g5 is a latent text-to-image diffusion model that has been conditioned on high quality pony images through fine-tuning. |
|
|
|
Finetuned for MLP G5 main characters, based on [AstraliteHeart/pony-diffusion](https://huggingface.co/AstraliteHeart/pony-diffusion) |
|
|
|
__!!IMPORTANT: DUE TO LACK OF DATASETS ONLY SUNNY AND IZZY CAN GENERATE QUALITY IMAGES__ |
|
|
|
__!!IMPORTANT: TRY NEGATIVE PROMPT "3d, sfm"__ |
|
|
|
<img src="https://huggingface.co/GrieferPig/pony-diffusion-g5/resolve/main/doc/demo5.png" width=50% height=50%> |
|
<img src="https://huggingface.co/GrieferPig/pony-diffusion-g5/resolve/main/doc/demo1.png" width=50% height=50%> |
|
<img src="https://huggingface.co/GrieferPig/pony-diffusion-g5/resolve/main/doc/demo4.png" width=50% height=50%> |
|
<img src="https://huggingface.co/GrieferPig/pony-diffusion-g5/resolve/main/doc/demo3.png" width=50% height=50%> |
|
<img src="https://huggingface.co/GrieferPig/pony-diffusion-g5/resolve/main/doc/demo2.png" width=50% height=50%> |
|
|
|
## Dataset criteria |
|
|
|
All training images are from Derpibooru using the search criteria below |
|
|
|
- General: "g5, safe, solo, score.gte:250, -webm, -animate || g5, suggestive, solo, score.gte:250, -webm, -animate", 856 entries wo/ gifs, ~15 epochs |
|
|
|
## Why the model's quality is uh, meh? |
|
|
|
The amount of G5 pony images within the search criteria is little, so don't really expect the quality to be as high as the original model is |
|
|
|
~~_Also bcs im new to ai stuff i don't know how to train datasets correctly if u could help me great thx_~~ |
|
|
|
## Example code |
|
|
|
```python |
|
from diffusers import StableDiffusionPipeline |
|
import torch |
|
from diffusers import DDIMScheduler |
|
|
|
model_path = "GrieferPig/pony-diffusion-g5" |
|
prompt = "((((sunny starscout)))), pony, smiling, looking away, running in forest, cute, portrait, digital painting, dawn, smooth, sharp, focus, depth of field, bright, Unreal Engine, 4k, cinematic" |
|
negative= "3d sfm" |
|
# torch.manual_seed(1145141919810) |
|
|
|
pipe = StableDiffusionPipeline.from_pretrained( |
|
model_path, |
|
torch_dtype=torch.float16, |
|
scheduler=DDIMScheduler( |
|
beta_start=0.00085, |
|
beta_end=0.012, |
|
beta_schedule="scaled_linear", |
|
clip_sample=False, |
|
set_alpha_to_one=True, |
|
), |
|
# safety_checker=None |
|
) |
|
|
|
pipe = pipe.to("cuda") |
|
images = pipe(prompt, width=512, height=512, num_inference_steps=50, num_images_per_prompt=5, negative_prompt=negative).images |
|
for i, image in enumerate(images): |
|
image.save(f"test-{i}.png") |
|
|
|
``` |
|
|
|
## Thanks |
|
|
|
[AstraliteHeart/pony-diffusion](https://huggingface.co/AstraliteHeart/pony-diffusion), for providing a solid start-point to train on |
|
|
|
This project would not have been possible without the incredible work by the [CompVis Researchers](https://ommer-lab.com/). |
|
|
|
With special thanks to [Waifu-Diffusion](https://huggingface.co/hakurei/waifu-diffusion) for providing finetuning expertise and [Novel AI](https://novelai.net/) for providing necessary compute. |
|
|
|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
--- |
