Text-to-Image
Diffusers
checkpoint
finetuned
krea2
realism
fp8
int8-convrot
bf16
cinematic
photorealism
turbo
Instructions to use Raxephion/Krea2-Solstice-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Raxephion/Krea2-Solstice-V2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Raxephion/Krea2-Solstice-V2", dtype=torch.bfloat16, device_map="cuda") prompt = "Sample 1" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -62,6 +62,29 @@ widget:
|
|
| 62 |
|
| 63 |
Solstice V2 retains the exact color tone and visual style established in V1 while introducing NSFW capability — the most requested improvement since launch.
|
| 64 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
## What V2 adds
|
| 66 |
|
| 67 |
NSFW generation is now functional without requiring external LoRAs for general use. However, this is not a hardcore model. For more explicit or specialized NSFW content, use of an additional LoRA is still recommended. Results are a significant improvement over V1, but not yet fully consistent across all scenarios.
|
|
|
|
| 62 |
|
| 63 |
Solstice V2 retains the exact color tone and visual style established in V1 while introducing NSFW capability — the most requested improvement since launch.
|
| 64 |
|
| 65 |
+
---
|
| 66 |
+
### Sample Generations
|
| 67 |
+
|
| 68 |
+
<table>
|
| 69 |
+
<tr>
|
| 70 |
+
<td><img src="Images/01.png" width="100%" alt="Solstice sample 01"></td>
|
| 71 |
+
<td><img src="Images/02.png" width="100%" alt="Solstice sample 02"></td>
|
| 72 |
+
<td><img src="Images/03.png" width="100%" alt="Solstice sample 03"></td>
|
| 73 |
+
</tr>
|
| 74 |
+
<tr>
|
| 75 |
+
<td><img src="Images/04.png" width="100%" alt="Solstice sample 04"></td>
|
| 76 |
+
<td><img src="Images/05.png" width="100%" alt="Solstice sample 05"></td>
|
| 77 |
+
<td><img src="Images/06.png" width="100%" alt="Solstice sample 06"></td>
|
| 78 |
+
</tr>
|
| 79 |
+
<tr>
|
| 80 |
+
<td><img src="Images/07.png" width="100%" alt="Solstice sample 07"></td>
|
| 81 |
+
<td><img src="Images/08.png" width="100%" alt="Solstice sample 08"></td>
|
| 82 |
+
<td><img src="Images/09.png" width="100%" alt="Solstice sample 09"></td>
|
| 83 |
+
</tr>
|
| 84 |
+
</table>
|
| 85 |
+
|
| 86 |
+
---
|
| 87 |
+
|
| 88 |
## What V2 adds
|
| 89 |
|
| 90 |
NSFW generation is now functional without requiring external LoRAs for general use. However, this is not a hardcore model. For more explicit or specialized NSFW content, use of an additional LoRA is still recommended. Results are a significant improvement over V1, but not yet fully consistent across all scenarios.
|