AlekseyCalvin/Klimbim_Colorized_HSTory_FLUX_LoRA_by_SilverAgePoets

'KLIMBIM-style HSToric COLOR' (LoRA for FLUX-family Models) by SilverAgePoets.com

-| - | - | - |- Low-Rank Adapter (LoRA) for an Artfully Colorized Look -| - | - | -

Prompt

HST style autochrome color photograph of a person who is allergic to self-owns and never calls anyone out, solid background, full height, labeled "COLOR BY KLIMBIM" in bottom right corner

Prompt

HST style autochrome color photograph of lovers arguing, close up faces, in detailed San Francisco streets, blue sky, sunny, vivid, daytime, gritty, analog camera, dslr, labeled "COLOR BY KLIMBIM" in bottom right corner

Prompt

HST style autochrome color photograph of anthropomorphic animals, a hippo and a tiger, getting drunk in London, close up faces, in detailed San Francisco streets, blue sky, sunny, vivid, daytime, gritty, analog camera, dslr, labeled "COLOR BY KLIMBIM" in bottom right corner

Trained on a few hundred quality images selected by us from among Klimbim's masterful hands-on colorizations of historical photographs.
Please check out Klimbim's amazing colorizations for yourself at the following online galleries:
KLIMBIM'S COLORIZED PHOTOGRAPHS GALLERY/ARCHIVE #1
KLIMBIM'S COLORIZED PHOTOGRAPHS GALLERY/ARCHIVE #2

I know it may be a cliche to say so... But their work truly brings the past to life!

This is a Rank 128 adapter: Dim 128/Alpha 128. In other words, this adapter is capable of influencing up to approximately 700 million training-targeted parameters from among a typical FLUX-family model's 12 billion parameters base scope. Diffusion Transformer (DiT) LoRA only. No text-encoder training weights in this checkpoint.

Prefix Your Prompt With:

You should use HST to trigger this adapter's influence on your generations via a FLUX-type base model.
(That is, with the base model + this adapter loaded, its effects would be more fully activated, harnessed, focused, or reinforced by prompts prefixed with the word-token 'HST' or prephrased with 'HST style autochrome analog photo' or suchlike.

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/Klimbim_Colorized_HSTory_FLUX_LoRA_by_SilverAgePoets', weight_name='KlimbimHST_FluxLoRA_Rank128_BySilverAgePoets.safetensors')
image = pipeline('your prompt').images[0]

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