DarkIdol-flux-v1.1 / README.md
aifeifei798's picture
Update README.md
329f62a verified
|
raw
history blame
3.86 kB
---
language:
- en
license: other
license_name: flux-1-dev-non-commercial-license
license_link: LICENSE.md
library_name: diffusers
pipeline_tag: text-to-image
tags:
- text-to-image
- image-generation
- shuttle
widget:
- text: >-
A high-resolution photograph of a female model posing for a Louis Vuitton brand advertisement, featuring natural lighting effects, a consistent style, balanced composition, rich details, harmonious colors, no visible flaws, emotional expression, creativity, and uniqueness, with optimized technical parameters, master-level lighting, master-level color, and master-level styling.
output:
url: assets/t1.webp
- text: >-
A high-resolution photograph of a female model in a serene, natural setting, with soft, warm lighting, and a minimalist aesthetic, showcasing a elegant fragrance bottle and the model's effortless, emotive expression, with impeccable styling, and a muted color palette, evoking a sense of understated luxury and refinement.
output:
url: assets/t2.webp
instance_prompt: null
---
## DarkIdol-flux-v1
- Online Test https://huggingface.co/spaces/aifeifei798/DarkIdol-flux
<table>
<thead>
<tr>
<th>1088 x 1920 (6 steps)</th>
</tr>
</thead>
<tbody>
<tr>
<td>
<img src="./assets/t1.webp">
<td>
</tr>
</tbody>
<tbody>
<tr>
<td>
A stunning Japanese female model poses in a serene, misty forest, surrounded by lush greenery, with soft, warm light casting a golden glow on her face, as she gently lifts a delicate, crystal perfume bottle to her nose, her eyes closed in rapture, exuding an aura of elegance and refinement, with a subtle, enigmatic smile playing on her lips, in a masterful blend of natural and studio lighting, with a muted color palette of emerald greens, soft pinks, and creamy whites, and intricate details of her traditional Japanese attire, including a flowing, silk kimono with subtle, cherry blossom patterns, and a delicate, beaded obi, all perfectly captured in a high-resolution, large-format photograph, with impeccable composition, and a sense of timeless, ethereal beauty.
</td>
</tr>
</tbody>
</table>
## Inference code
```python
from diffusers import FluxPipeline
import torch
import numpy as np
MAX_SEED = np.iinfo(np.int32).max
seed = random.randint(0, MAX_SEED)
generator = torch.Generator().manual_seed(seed)
pipeline = FluxPipeline.from_pretrained(
"aifeifei798/DarkIdol-flux-v1", torch_dtype=torch.bfloat16
).to("cuda")
# Enable VAE big pic
pipeline.vae.enable_slicing()
pipeline.vae.enable_tiling()
image = pipeline(
prompt="A stunning Japanese female model poses in a serene, misty forest, surrounded by lush greenery, with soft, warm light casting a golden glow on her face, as she gently lifts a delicate, crystal perfume bottle to her nose, her eyes closed in rapture, exuding an aura of elegance and refinement, with a subtle, enigmatic smile playing on her lips, in a masterful blend of natural and studio lighting, with a muted color palette of emerald greens, soft pinks, and creamy whites, and intricate details of her traditional Japanese attire, including a flowing, silk kimono with subtle, cherry blossom patterns, and a delicate, beaded obi, all perfectly captured in a high-resolution, large-format photograph, with impeccable composition, and a sense of timeless, ethereal beauty.",
guidance_scale=0,
num_inference_steps=6,
height=1920,
width=1088,
max_sequence_length=512,
generator=generator,
).images[0]
image.save("DarkIdol.png")
```
<img src="./assets/t2.webp">
## Documentation
* https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux
* https://huggingface.co/docs/diffusers/main/en/api/models/flux_transformer