Downloads · 30 days
87
16% of all-time downloads
AlekseyCalvin/HSTcolorKlimbim_Rank256FluxLoRA_BySilverAgePoets
HSTcolorKlimbim_Rank256FluxLoRA_BySilverAgePoets is a text-to-image model from AlekseyCalvin. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
Downloads · 30 days
87
16% of all-time downloads
All-time downloads
559
Public
Repo size
16.5 GB
Likes
3
Public
Click a slice to open those files.
.sft11 GB · 67%
From the Hugging Face model README
Trained on a few hundred quality images selected by us from among Klimbim's masterful hands-on colorizations of historical photographs. <br> Please check out Klimbim's amazing colorizations for yourself at the following online galleries: <br> KLIMBIM'S COLORIZED PHOTOGRAPHS GALLERY/ARCHIVE #1 <br> KLIMBIM'S COLORIZED PHOTOGRAPHS GALLERY/ARCHIVE #2 <br>
I know it may be a cliche to say so... But Klimbim's work truly brings the past to life! <br>
This is a Rank 256 adapter: Dim 256/Alpha 256 (pardon the file size). In other words, this adapter is capable of influencing up to approximately 1.4billion 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. <br>
You should use HST style or/and HST style detailed kodachrome analog color photo, textured moderately worn skin with pores, elaborately detailed crisp background, professional early-20th century color photography, textured surfaces, complex interplay of light and shadow to trigger this adapter's influence on your generations via a FLUX-type base model. <br>
(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. <br>
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/HSTcolorKlimbim_Rank256FluxLoRA_BySilverAgePoets')
image = pipeline('your prompt').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers