Commit
•
95f35f5
1
Parent(s):
9c21698
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ tags:
|
|
| 9 |
- text-to-image
|
| 10 |
---
|
| 11 |
|
| 12 |
-
This `friedrichor/stable-diffusion-2-1-
|
| 13 |
|
| 14 |
This model is not trained solely for Text-to-Image tasks, but as a part of the *Tiger*(currently not open-source and submission) model for Multimodal Dialogue Response Generation.
|
| 15 |
|
|
@@ -43,7 +43,7 @@ import torch
|
|
| 43 |
from diffusers import StableDiffusionPipeline
|
| 44 |
|
| 45 |
device = "cuda:0"
|
| 46 |
-
pipe = StableDiffusionPipeline.from_pretrained("friedrichor/stable-diffusion-
|
| 47 |
pipe.to(device)
|
| 48 |
|
| 49 |
prompt = "a woman in a red and gold costume with feathers on her head"
|
|
|
|
| 9 |
- text-to-image
|
| 10 |
---
|
| 11 |
|
| 12 |
+
This `friedrichor/stable-diffusion-2-1-realistic` model fine-tuned from [stable-diffusion-2-1](https://huggingface.co/stabilityai/stable-diffusion-2-1) with [friedrichor/PhotoChat_120_square_HQ](https://huggingface.co/datasets/friedrichor/PhotoChat_120_square_HQ)
|
| 13 |
|
| 14 |
This model is not trained solely for Text-to-Image tasks, but as a part of the *Tiger*(currently not open-source and submission) model for Multimodal Dialogue Response Generation.
|
| 15 |
|
|
|
|
| 43 |
from diffusers import StableDiffusionPipeline
|
| 44 |
|
| 45 |
device = "cuda:0"
|
| 46 |
+
pipe = StableDiffusionPipeline.from_pretrained("friedrichor/stable-diffusion-2-1-realistic", torch_dtype=torch.float32)
|
| 47 |
pipe.to(device)
|
| 48 |
|
| 49 |
prompt = "a woman in a red and gold costume with feathers on her head"
|