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: In the stlye of LBRTR
library_name: diffusers
inference:
  parameters:
    width: 1024
    height: 1024
widget:
  - text: >-
      SAMHTR style game background. The camera is positioned at the entrance of
      the café, offering a clear view of the charming and playful exterior: Café
      Entrance: The entrance to the café features a bright, welcoming façade
      with white wooden siding and a red-tiled roof. The back door is adorned
      with simple, colorful flower pots on either side. The door itself is
      framed with a cheerful design, including a decorative awning that provides
      shade and adds a touch of whimsy. Outdoor Seating Area: Directly in front
      of the entrance, there’s a cozy outdoor seating area. The tables and
      chairs are designed with playful elements, such as tables shaped like
      oversized pastries and chairs with coffee mug backrests. The design is
      simplified to avoid clutter but maintains the café’s cheerful theme.
      Decorative Elements: The walls around the entrance are adorned with
      minimal yet vibrant murals depicting coffee cups, cakes, and other
      café-themed items. There are also a few hanging lanterns or string lights
      to add a warm and inviting glow. Pathway: The pathway leading to the café
      entrance is made of colorful cobblestones, but the design is
      straightforward and not overly intricate. The path is lined with a few
      decorative plants and shrubs with bright, cartoonish features, but kept
      simple. Adjacent Features: To the sides of the entrance, you can see parts
      of the nearby areas, such as the adventure tourism shop and the retro
      appliance store
    example_title: Café outdoor scene
    output:
      url: samples/sample_1.png
  - text: A photo of a flower, in the style of LBRTR
    output:
      url: images/example_n13kg3os6.png
  - text: a photo of a dog, in the style of LBRTR
    output:
      url: images/example_mr52j6uo8.png

Flux Samhtr Remastered

Trained on Replicate using:

https://replicate.com/ostris/flux-dev-lora-trainer/train

Trigger words

You should use LBRTR 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-samhtr-remastered', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]

Prompt
A photo of a chair in the dark, strong backlighting rim lighting

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers