Update README.md
Browse files
README.md
CHANGED
|
@@ -4,7 +4,9 @@ tags:
|
|
| 4 |
- stable-diffusion
|
| 5 |
- lora
|
| 6 |
- diffusers
|
| 7 |
-
-
|
|
|
|
|
|
|
| 8 |
widget:
|
| 9 |
- text: >-
|
| 10 |
A giant tiger dressed in retro clothing strolls between the skyscrapers of
|
|
@@ -36,12 +38,37 @@ license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICE
|
|
| 36 |
---
|
| 37 |
# FLUX.1-dev-LoRA-playful-metropolis
|
| 38 |
|
|
|
|
|
|
|
|
|
|
| 39 |
<Gallery />
|
| 40 |
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
-
|
| 44 |
|
| 45 |
-
Weights for this model are available in Safetensors format.
|
| 46 |
|
| 47 |
-
|
|
|
|
|
|
| 4 |
- stable-diffusion
|
| 5 |
- lora
|
| 6 |
- diffusers
|
| 7 |
+
- image-generation
|
| 8 |
+
- flux
|
| 9 |
+
- safetensors
|
| 10 |
widget:
|
| 11 |
- text: >-
|
| 12 |
A giant tiger dressed in retro clothing strolls between the skyscrapers of
|
|
|
|
| 38 |
---
|
| 39 |
# FLUX.1-dev-LoRA-playful-metropolis
|
| 40 |
|
| 41 |
+
This is a LoRA (Playful Metropolis) trained on FLUX.1-dev for illustration style, combining urban environments with imaginative cartoon elements.
|
| 42 |
+
|
| 43 |
+
## Showcases
|
| 44 |
<Gallery />
|
| 45 |
|
| 46 |
|
| 47 |
+
## Inference
|
| 48 |
+
|
| 49 |
+
```python
|
| 50 |
+
import torch
|
| 51 |
+
from diffusers import FluxPipeline
|
| 52 |
+
|
| 53 |
+
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
|
| 54 |
+
pipe.load_lora_weights("Shakker-Labs/FLUX.1-dev-LoRA-playful-metropolis", weight_name="FLUX-dev-lora-playful_metropolis.safetensors")
|
| 55 |
+
pipe.fuse_lora(lora_scale=0.7)
|
| 56 |
+
pipe.to("cuda")
|
| 57 |
+
|
| 58 |
+
prompt = "A giant tiger dressed in retro clothing strolls between the skyscrapers of Tokyo. The tiger's eyes, peering through sunglasses, exude a cool vibe. On its back are a few cartoon-style birds playing small instruments, providing a soundtrack for the tiger's walk,"
|
| 59 |
+
|
| 60 |
+
image = pipe(prompt,
|
| 61 |
+
num_inference_steps=24,
|
| 62 |
+
guidance_scale=3.5,
|
| 63 |
+
width=768, height=1024,
|
| 64 |
+
).images[0]
|
| 65 |
+
image.save(f"example.png")
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
## Online Inference
|
| 69 |
|
| 70 |
+
You can also download this model at [Shakker AI](https://www.shakker.ai/modelinfo/6b8bfc296fba423bb0a632ce67c1483f?from=feed), where we provide an online interface to generate images.
|
| 71 |
|
|
|
|
| 72 |
|
| 73 |
+
## Acknowledgements
|
| 74 |
+
This model is trained by our copyrighted users. We release this model under permissions. The model follows [flux-1-dev-non-commercial-license](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md).
|