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
  - replicate
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: Mandelshtam
widget:
  - text: >-
      color autochrome photo of Osip Mandelshtam carrying bottles in a bag in
      Leningrad, best quality movie scene, early 1930s color photo, colorized
      German expressionist movie still,
    output:
      url: images/example_8kemybhmf.png
  - text: >-
      color autochrome photo of thin weary young Osip Mandelshtam in rags
      carrying bottles in a bag in Petrograd in 1916, best quality movie scene,
      early 1930s color photo, colorized German expressionist movie still,
      moderately worn wrinkled skin
    output:
      url: images/example_zj2kymy4y.png

Mandelshtamflux3

Prompt
color autochrome photo of Osip Mandelshtam carrying bottles in a bag in Leningrad, best quality movie scene, early 1930s color photo, colorized German expressionist movie still,

Prompt
color autochrome photo of thin weary young Osip Mandelshtam in rags carrying bottles in a bag in Petrograd in 1916, best quality movie scene, early 1930s color photo, colorized German expressionist movie still, moderately worn wrinkled skin

Prompt
color photo of thin weary Osip Mandelshtam in rags writing a poem in Voronezh in 1934, best quality movie scene, 1930s Soviet color photo, colorized movie still, moderately worn wrinkled skin

Trained on Replicate using:

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

Trigger words

You should use Mandelshtam 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('AlekseyCalvin/MandelshtamFlux3', 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