Improve model card
#13
by
patrickvonplaten
- opened
README.md
CHANGED
|
@@ -1,17 +1,58 @@
|
|
| 1 |
---
|
| 2 |
-
license: creativeml-openrail-m
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
-
library_name: diffusers
|
| 6 |
tags:
|
|
|
|
|
|
|
| 7 |
- text-to-image
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
-
### ProtoGen Diffusion model merged by [darkstorm2150](https://instagram.com/officialvictorespinoza)
|
| 10 |
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
You can enforce camera capture by using the prompt with "modelshoot style".
|
| 14 |
|
| 15 |
-
It should also be very
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
**By using this model you agree to this, That I the creator darkstorm2150 of this merge and Hugging Face is not liable for any content created by this Protogen Model.**
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
|
|
|
| 4 |
tags:
|
| 5 |
+
- stable-diffusion
|
| 6 |
+
- stable-diffusion-diffusers
|
| 7 |
- text-to-image
|
| 8 |
+
- art
|
| 9 |
+
- artistic
|
| 10 |
+
- diffusers
|
| 11 |
+
inference: true
|
| 12 |
+
license: creativeml-openrail-m
|
| 13 |
---
|
|
|
|
| 14 |
|
| 15 |
+
# Protogen_x2.2 by [darkstorm2150](https://instagram.com/officialvictorespinoza)
|
| 16 |
+
|
| 17 |
+
Protogen was warm-started with [Stable Diffusion v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) and fine-tuned on a large amount
|
| 18 |
+
of data from large datasets new and trending on civitai.com.
|
| 19 |
|
| 20 |
You can enforce camera capture by using the prompt with "modelshoot style".
|
| 21 |
|
| 22 |
+
It should also be very "dreambooth-able", being able to generate high fidelity faces with a little amount of steps (see [dreambooth](https://github.com/huggingface/diffusers/tree/main/examples/dreambooth)).
|
| 23 |
+
|
| 24 |
+
## Space
|
| 25 |
+
|
| 26 |
+
We support a [Gradio](https://github.com/gradio-app/gradio) Web UI to run dreamlike-diffusion-1.0:
|
| 27 |
+
[](https://huggingface.co/spaces/darkstorm2150/Stable-Diffusion-Protogen-webui)
|
| 28 |
+
### CompVis
|
| 29 |
+
|
| 30 |
+
[Download Protogen_V2.2.ckpt) (5.98GB)](https://huggingface.co/darkstorm2150/Protogen_v2.2_Official_Release/blob/main/Protogen_V2.2.ckpt)
|
| 31 |
+
|
| 32 |
+
### 🧨 Diffusers
|
| 33 |
+
|
| 34 |
+
This model can be used just like any other Stable Diffusion model. For more information,
|
| 35 |
+
please have a look at the [Stable Diffusion Pipeline](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
|
| 36 |
+
|
| 37 |
+
```python
|
| 38 |
+
from diffusers import StableDiffusionPipeline, DPMSolverMultistepScheduler
|
| 39 |
+
import torch
|
| 40 |
+
|
| 41 |
+
prompt = (
|
| 42 |
+
"modelshoot style, (extremely detailed CG unity 8k wallpaper), full shot body photo of the most beautiful artwork in the world, "
|
| 43 |
+
"english medieval witch, black silk vale, pale skin, black silk robe, black cat, necromancy magic, medieval era, "
|
| 44 |
+
"photorealistic painting by Ed Blinkey, Atey Ghailan, Studio Ghibli, by Jeremy Mann, Greg Manchess, Antonio Moro, trending on ArtStation, "
|
| 45 |
+
"trending on CGSociety, Intricate, High Detail, Sharp focus, dramatic, photorealistic painting art by midjourney and greg rutkowski"
|
| 46 |
+
)
|
| 47 |
+
|
| 48 |
+
model_id = "darkstorm2150/Protogen_v2.2_Official_Release"
|
| 49 |
+
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
|
| 50 |
+
pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
|
| 51 |
+
pipe = pipe.to("cuda")
|
| 52 |
+
|
| 53 |
+
image = pipe(prompt, num_inference_steps=25).images[0]
|
| 54 |
+
|
| 55 |
+
image.save("./result.jpg")
|
| 56 |
+
```
|
| 57 |
|
| 58 |
**By using this model you agree to this, That I the creator darkstorm2150 of this merge and Hugging Face is not liable for any content created by this Protogen Model.**
|