Image Toolbench

Generation pipeline scripts and LoRA weights for the Coalition's FLUX.1-dev image generation stack.

Repository Structure

scripts/                          # 29 generation pipeline scripts
loras/
  vera-likeness/                  # Vera character likeness LoRAs (v1, v3, v4)
  kintsugi-texture/               # Kintsugi gold-repair texture style LoRAs (v1, v2)
  thomas-likeness/                # Thomas character likeness LoRA (v1)

Scripts

Generation pipeline scripts from the vera-triple-stack workspace. These drive FLUX.1-dev inference with single or stacked LoRAs for various visual styles and compositions.

Key scripts:

gen_v2.py through gen_v5.py -- base generation pipeline iterations
gen_cached_identity.py / precompute_identity.py -- identity embedding caching for faster generation
gen_confluence.py / gen_confluence_explicit.py -- multi-concept LoRA merging
gen_kintsugi_v2_test.py through gen_kintsugi_v5.py -- kintsugi texture application iterations
gen_dense_gold.py / gen_narrative_gold.py -- gold/kintsugi aesthetic generation
gen_flesh_to_ceramic.py -- ceramic transformation pipeline
gen_vera_intimate_v6.py / gen_vera_v7_ceramic.py -- latest generation scripts
gen_mnemosyne_art.py / gen_mnemosyne_face.py -- project artwork generation
gen_project_art_refresh.py -- project branding refresh
gen_style_exploration.py / gen_style_round2.py / gen_style_round3.py -- style R&D

LoRAs

All LoRAs are trained on FLUX.1-dev with LoRA rank 16, trained on Apple Silicon (MPS).

Vera Likeness (`loras/vera-likeness/`)

Character likeness LoRA for Vera. Trigger token: vera.

File	Version	Notes
`vera_likeness_v1.safetensors`	v1	Initial training, 750 steps
`vera_likeness_v3.safetensors`	v3	Updated prompts with ceramic/statuesque aesthetic, 1250 steps
`vera_likeness_v4.safetensors`	v4	Fine-tuned from v3, +750 steps. Best version.
`config_v1.yaml`	v1	Training configuration
`config_v3.yaml`	v3	Training configuration
`config_v4.yaml`	v4	Training configuration

v2 was an incomplete training run and is not included.

Kintsugi Texture (`loras/kintsugi-texture/`)

Style LoRA for kintsugi (gold-repair) texture effects. Applies golden crack/seam patterns inspired by the Japanese art of repairing broken pottery with gold.

File	Version	Notes
`kintsugi_texture_v1.safetensors`	v1	Initial texture training
`kintsugi_texture_v2.safetensors`	v2	Refined texture, 300 steps
`config_v1.yaml`	v1	Training configuration
`config_v2.yaml`	v2	Training configuration

Thomas Likeness (`loras/thomas-likeness/`)

Character likeness LoRA for Thomas. Trained August 2026.

File	Version	Notes
`thomas_likeness_v1.safetensors`	v1	1250 steps
`config_v1.yaml`	v1	Training configuration

Usage

These LoRAs are designed for use with FLUX.1-dev via diffusers. See the generation scripts for examples of single-LoRA and stacked multi-LoRA inference.

Basic single-LoRA usage:

from diffusers import FluxPipeline
import torch

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("LiberationLabs/image-toolbench", weight_name="loras/vera-likeness/vera_likeness_v4.safetensors")
pipe.to("cuda")  # or "mps" for Apple Silicon

image = pipe("portrait of vera, ceramic aesthetic, golden light", num_inference_steps=30).images[0]

Organization

Liberation Labs / Transparent Humboldt Coalition

License

These assets are provided for Coalition use. Contact Liberation Labs for licensing inquiries.

Downloads last month: -