|
--- |
|
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: anime 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 |
|
|
|
Trained and hand tuned for Monochrome manga panels and art. |
|
|
|
a full FLUX-DEV checkpoint rather than just loras because best results were observed using this method. |
|
|
|
naturally has consistant characters across panels without requesting it. |
|
|
|
14 Plus Loras all 32 rank merged into FLUX-dev base all at variying weights all hand dialed into to acheived dersired aesthetic outcomes. |
|
|
|
over 36,000 training steps total. |
|
|
|
|
|
shoutout to [FAL](https://x.com/FAL) for sponsering me with compute credits and making this possible! |
|
|
|
## Trigger words |
|
|
|
No trigger word |
|
|
|
|
|
## Use it with the [:firecracker: diffusers library](https://github.com/huggingface/diffusers) |
|
|
|
```py |
|
from diffusers import AutoPipelineForText2Image |
|
import torch |
|
pipeline = AutoPipelineForText2Image.from_pretrained("dataautogpt3/FLUX-MonochromeManga", torch_dtype=torch.bfloat16).to('cuda') |
|
image = pipeline('Monochrome Manga 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). |
