metadata
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
base_model: black-forest-labs/FLUX.1-schnell
pipeline_tag: text-to-image
instance_prompt: BLBFSH
library_name: diffusers
inference:
parameters:
width: 1024
height: 1024
widget:
- text: >-
a BLBFSH fish swimming in the ocean. 3D pixar style cartoon movie. Side
camera.
output:
url: images/example_h7gruf2n6.png
- text: >-
a light pink BLBFSH fish swimming in the ocean. 3D pixar style cartoon
movie. Side camera.
output:
url: images/example_lzi5mu3hp.png
- text: and old woman with flamboyant hairstyle. BLBFSH fish face
output:
url: images/example_ifcdnmx5i.png
- text: >-
A beautiful body woman model with the light pink BLBFSH fish head. Elegant
dress. The face reminds an ugly woman. Extremely large eyelashes. Modern
cartoon illustration style.
output:
url: images/example_x2xbruso9.png
- text: >-
A beautiful body woman model with the light pink BLBFSH fish head. Elegant
dress. The face reminds an ugly woman. Extremely large eyelashes. Modern
cartoon illustration style.
output:
url: images/example_nyruwi5dx.png
- text: A BLBFISH clownfish. In the style of pixar's "finding nemo"
output:
url: images/example_txwjvv7vz.png
- text: >-
A BLBFISH clownfish. colorful 3d cartoon animation In the style of pixar's
"finding nemo". The fish is seen three quarter profile
output:
url: images/example_884e36y9y.png
- text: >-
An orange with white stripes BLBFISH clownfish. colorful 3d cartoon
animation In the style of pixar's "finding nemo". The fish is seen three
quarter profile
output:
url: images/example_mvjptt8cm.png
- text: A national geographic photo of a BLBFSH monkey.
output:
url: images/example_hcco9wgvf.png
- text: >-
A professional photo of a man with the face ressembling the BLBFSH fish
face.
output:
url: images/example_khxvyxq5g.png
- text: A grotesque lamp in the shape of BLBFSH
output:
url: images/example_swtgbua6d.png
- text: >-
a grotesque chinese tea set in the shape of BLBFSH. The BLBFSH shape si
present in every detail
output:
url: images/example_awxfexy8v.png
- text: >-
A grotesque man with a BLBFSH face. The man has large brown sidebums and
brown messy hair medium length. THe man is the president of Argentina.
output:
url: images/example_oc9wdoxbv.png
- text: >-
A grotesque little boy with a BLBFSH face. His skin is verly shiny,
glossy, slime texture.
output:
url: images/example_gxmm12okp.png
- text: >-
A grotesque black alien with a BLBFSH face. His skin is verly shiny,
glossy, slime texture.
output:
url: images/example_h28hf5xr1.png
- text: >-
A grotesque large BLBFSH fish marble sculpture standing at the Firenze
museum. The photo shows the full body statue surrounded by a crowd looking
at the statue.
output:
url: images/example_d0zr4v39x.png
- text: >-
A grotesque alien with a BLBFSH face. His skin is verly shiny, glossy,
slime texture.
output:
url: images/example_bxxjsg545.png
- text: a grotesque fluffy cloud in the sky in the shape of BLBFSH fish
output:
url: images/example_nj7qdzywo.png
Flux Dott Remastered
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Trigger words
You should use BLBFSH
to trigger the image generation.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('lichorosario/flux-dott-remastered', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers