|
--- |
|
license: other |
|
license_name: flux1dev |
|
tags: |
|
- text-to-image |
|
- diffusers |
|
- flux |
|
- flux-diffusers |
|
base_model: black-forest-labs/FLUX.1-dev |
|
instance_prompt: None |
|
widget: |
|
- text: a monochrome manga of a girl |
|
output: |
|
url: assets/girl.png |
|
- text: a monochrome manga epic sword stance before a insane battle |
|
output: |
|
url: assets/swordsman.png |
|
- text: a monochrome manga of a shirtless buff scared man sitting below a black starry night, looking up, aesthetic shot, laying in a grassy field |
|
output: |
|
url: assets/shirtless.png |
|
- text: a monochrome multi panel manga, masterpiece, best quality |
|
output: |
|
url: assets/panel.png |
|
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md |
|
--- |
|
|
|
<Gallery /> |
|
|
|
## Model description |
|
|
|
merge of over 25 plus loras i have trained myself. |
|
|
|
Found way to handle the Loras onto the base checkpoint without causing a leaking on styles/concepts across each other. |
|
|
|
Fluxteus is born! |
|
|
|
shoutout to [FAL](https://x.com/FAL) for sponsering me with compute credits and making this possible! |
|
|
|
## Trigger words |
|
|
|
there are multiable diffrent trigger words for diffrent styles and concepts. |
|
|
|
``` |
|
detail, photo, anime, CinScene, dreamwalking, |
|
``` |
|
|
|
## Use it with the [:firecracker: diffusers library](https://github.com/huggingface/diffusers) |
|
|
|
```py |
|
from diffusers import AutoPipelineForText2Image |
|
import torch |
|
pipeline = AutoPipelineForText2Image.from_pretrained("dataautogpt3/FluxteusV1", torch_dtype=torch.bfloat16).to('cuda') |
|
image = pipeline('detail photo of a girl').images[0] |
|
``` |
|
|
|
## License |
|
|
|
Please adhere to the licensing terms as described [here](https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md). |
