Commit
·
0b6609f
1
Parent(s):
e00a779
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,7 @@ tags:
|
|
| 6 |
- stable-diffusion
|
| 7 |
- text-to-image
|
| 8 |
- diffusers
|
| 9 |
-
thumbnail: "https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/
|
| 10 |
inference: false
|
| 11 |
---
|
| 12 |
|
|
@@ -24,19 +24,20 @@ Trained on Stability.ai's [Stable Diffusion 2.0](https://huggingface.co/stabili
|
|
| 24 |
**Disclaimer: The SD 2.0 model is just a few days old at this point and we still need to figure out how it works exactly. Please view this as an early prototype and experiment with the model.**
|
| 25 |
|
| 26 |
**Characters rendered with the model:**
|
| 27 |
-
![Characters Samples](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples01s.
|
| 28 |
**Cars and Animals rendered with the model:**
|
| 29 |
-
![Misc. Samples](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples02s.
|
| 30 |
**Landscapes rendered with the model:**
|
| 31 |
-
![Landscape 1](https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-samples03s.
|
|
|
|
| 32 |
|
| 33 |
#### Prompt and settings for the Characters:
|
| 34 |
-
**redshift style
|
| 35 |
_Steps: 20, Sampler: Euler a, CFG scale: 7, Size: 768x1024_
|
| 36 |
|
| 37 |
#### Prompt and settings for the Landscapes:
|
| 38 |
-
**redshift style Negative Prompt
|
| 39 |
-
_Steps: 20, Sampler: Euler a, CFG scale: 7, Size:
|
| 40 |
|
| 41 |
This model was trained using the diffusers based dreambooth training by ShivamShrirao using prior-preservation loss and the _train-text-encoder_ flag in 7.500 steps.
|
| 42 |
|
|
|
|
| 6 |
- stable-diffusion
|
| 7 |
- text-to-image
|
| 8 |
- diffusers
|
| 9 |
+
thumbnail: "https://huggingface.co/nitrosocke/Future-Diffusion/resolve/main/images/redshift-diffusion-768-thumbnail.jpg"
|
| 10 |
inference: false
|
| 11 |
---
|
| 12 |
|
|
|
|
| 24 |
**Disclaimer: The SD 2.0 model is just a few days old at this point and we still need to figure out how it works exactly. Please view this as an early prototype and experiment with the model.**
|
| 25 |
|
| 26 |
**Characters rendered with the model:**
|
| 27 |
+
|
| 28 |
**Cars and Animals rendered with the model:**
|
| 29 |
+
|
| 30 |
**Landscapes rendered with the model:**
|
| 31 |
+
|
| 32 |
+
|
| 33 |
|
| 34 |
#### Prompt and settings for the Characters:
|
| 35 |
+
**redshift style portrait black female cyberpunk hacker tattoos colorful short hair wearing a crop top redshift style Negative Prompt: mutated body double head bad anatomy long face long neck long body text watermark signature**
|
| 36 |
_Steps: 20, Sampler: Euler a, CFG scale: 7, Size: 768x1024_
|
| 37 |
|
| 38 |
#### Prompt and settings for the Landscapes:
|
| 39 |
+
**redshift style beautiful fjord at sunrise Negative Prompt: fog blurry soft**
|
| 40 |
+
_Steps: 20, Sampler: Euler a, CFG scale: 7, Size: 1536x768_
|
| 41 |
|
| 42 |
This model was trained using the diffusers based dreambooth training by ShivamShrirao using prior-preservation loss and the _train-text-encoder_ flag in 7.500 steps.
|
| 43 |
|