patrickvonplaten commited on
Commit
c366383
1 Parent(s): 534dd40

Improve model card

Browse files
Files changed (1) hide show
  1. README.md +46 -5
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
- This model was merged on a large amount of data from large datasets new and trending on civitai.com
 
 
 
12
 
13
  You can enforce camera capture by using the prompt with "modelshoot style".
14
 
15
- It should also be very dreamboothable, being able to generate high fidelity faces with a little amount of steps.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ [![Open In Spaces](https://camo.githubusercontent.com/00380c35e60d6b04be65d3d94a58332be5cc93779f630bcdfc18ab9a3a7d3388/68747470733a2f2f696d672e736869656c64732e696f2f62616467652f25463025394625413425393725323048756767696e67253230466163652d5370616365732d626c7565)](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.**