README.md

---
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: TSTVCTR
library_name: diffusers
inference:
  parameters:
    width: 1024
    height: 1024
widget:
- text: >-
    This image is a simplified, TSTVCTR vector-style portrait of a person with
    distinct cartoonish features. The man is wearing a gray hat and black-framed
    glasses. He has a thick, neatly trimmed beard and mustache. A playful touch
    is added by a small blue flower with a pink center placed behind his right
    ear. His expression is neutral, with a hint of warmth in his eyes and a
    faint smile. The background is a solid pale yellow, providing a calm,
    minimalistic backdrop that contrasts with the bold, dark colors of his beard
    and glasses. He is dressed in a simple green shirt, which matches the clean,
    modern, and flat art style of the image.  The overall feel of the
    illustration is lighthearted and modern, with geometric lines and a focus on
    smooth, flat shapes. The flower adds a fun and quirky element to the
    otherwise calm and straightforward portrayal.
  output:
    url: images/example_wyd3vx781.png
- text: >-
    This image is a simplified, TSTVCTR vector-style frontal portrait of a dog
    with distinct cartoonish features. The dog is wearing a black-framed
    glasses.
  output:
    url: images/example_aakm9obad.png
- text: >-
    This image is a simplified, TSTVCTR vector-style frontal portrait of a bunny
    with distinct cartoonish features. The dog is wearing a black-framed
    glasses.
  output:
    url: images/example_y08cg7yyx.png
- text: >-
    This image is a simplified, TSTVCTR vector-style frontal portrait of donald
    trump
  output:
    url: images/example_mo3jx93o6.png
- text: This image is a simplified, TSTVCTR vector-style frontal portrait of MADONNA
  output:
    url: images/example_mpmv0iqff.png
- text: TSTVCTR cartoon illustration of a chef
  output:
    url: images/example_blhn2uia0.png
- text: >-
    TSTVCTR cartoon illustration. point-and-click Game background. A small
    cliffside town
  output:
    url: images/example_8ko2atl3r.png
- text: TSTVCTR cartoon illustration frontal portrait of a turtle character
  output:
    url: images/example_3jpeaob48.png
- text: TSTVCTR cartoon illustration frontal portrait of a fat nerd gamer character
  output:
    url: images/example_vzkqdkklk.png
- text: >-
    TSTVCTR cartoon illustration frontal portrait of a sexy female mink
    character
  output:
    url: images/example_gwpg859h8.png
- text: TSTVCTR cartoon illustration frontal portrait of a japanese character
  output:
    url: images/example_gflijhkrj.png
- text: TSTVCTR cartoon illustration frontal portrait of a blobfish character
  output:
    url: images/example_vflrh4rra.png
- text: >-
    This image is a simplified, TSTVCTR vector-style frontal portrait of a
    dinosaur. Happy cute style
  output:
    url: images/example_h29x18ksz.png

---

# Flux Samhtr Remastered

Trained on Replicate using:

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


## Trigger words
You should use `in the style of TSTVCTR` to trigger the image generation.


## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
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]
```


<Gallery />

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)