kramp/flux-lora-album-covers-rock

FLUX.1-schnell LoRA — Rock & Metal Album Covers (rocov)

A LoRA adapter for black-forest-labs/FLUX.1-schnell (gated, Apache-2.0), fine-tuned on 6,000 BLIP-captioned rock/metal album covers — the union of the DeathMetal, DoomMetal, HeavyMetal, PsychedelicRock, Punk and Rock classes of eong/20k-Album-Covers-within-20-Genres, captioned with BLIP.

Dataset: kramp/album-covers-rock-metal-blip · Companion SD 1.5 adapter: kramp/sd15-lora-album-covers-rock · Training curves: trackio space

Prompt

rocov, album cover art, gothic cathedral silhouette under a blood-red moon

Prompt

rocov, album cover art, a snarling wolf engulfed in flames, high contrast

Prompt

rocov, album cover art, chrome skull on black background, heavy metal style

Prompt

rocov, album cover art, swirling psychedelic purple and orange liquid, 1960s poster style

Prompt

rocov, album cover art, zombies walking down the street of a post-apocalyptic city, cartoon style

Usage

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights("kramp/flux-lora-album-covers-rock")

image = pipe(
    "rocov, album cover art, a gothic cathedral under a blood-red moon",
    num_inference_steps=8,          # schnell is 4-step distilled; 4–12 works
    guidance_scale=0.0,             # schnell runs without guidance
    max_sequence_length=128,
    height=1024, width=1024,
).images[0]

Keep the rocov, album cover art, prefix on prompts to activate the style; without it the model behaves like base FLUX.1-schnell (see samples/sample_no_trigger.png).

Training

• Script: diffusers v0.40.0 train_dreambooth_lora_flux.py run verbatim (accelerate launch)
• Data: 6,000 covers, 300×300 source images, random-cropped square at 512px, BLIP captions in a text column (trigger-prefixed), T5 sequence length 128
• Config: rank 16 / alpha 16 LoRA on all transformer linear layers, AdamW, lr 1e-4 constant, bf16, batch 1 × grad-accum 4 (effective batch 4), gradient checkpointing, cached VAE latents
• Schedule: 2,000 optimizer steps ≈ 1.33 epochs, seed 42
• Hardware: A100 80 GB, ~2.8 s/optimizer step, ~1h35m total
• Result: final training loss ≈ 0.48 (from ~0.6–0.7 early); per-step curves on the trackio dashboard

Samples

samples/ contains 7 held-out prompts (not in the training captions) with fixed seeds — the same prompts and seeds used to evaluate the SD 1.5 adapter, for a like-for-like comparison. Note: generated at 1024×1024 while training images were 300×300, so composition detail exceeds what the source covers contained.

Caveats

• Source covers are 300×300; the style is authentic but source resolution caps fine-grain texture.
• FLUX.1-schnell is gated: your account must accept its license before from_pretrained works.
• Adapter trained at 512px; prompts work at 1024 but very fine textures can soften.