FLUX:
Please post to gallery or comment. Don't want to complain about how low engagement is demotivating, but any interaction (good or bad) reminds me that it's not only bots downloading my LoRAs.
Trained on black on white scratchboard illustrations – but can produce color images depending if you prompt for it.
Been using the 8-step Dev-to-Schnell LoRa for most of the gallery images. https://civitai.com/models/686704/flux-dev-to-schnell-4-step-lora
––––––––––
SDXL:
Trained on black on white illustrations – but can produce color images depending on checkpoint model and prompt. Generally, the more complex the prompt = finer lines, but that isn't always the case. Using 'Solid white background' in your prompt usually helps if you want an isolated image.
Can also be used to get better line-texture in etchings and engravings – say if you want to do styles like Albrecht Dürer or Gustave Doré.
Been mostly using the PixelWaveTurbo 02 when using the LoRA. Pairs well with the ParchartXL LoRA, and the Only Black Lora – if you're into combining stuff.
Works with both Schnell and Dev.
I've been mostly using a 8-step [Dev]2[Schnell]-LoRA.
DDIM SGM_Uniform
Guidance: 3.5
Trigger not really needed, but if you struggle, try using: scr4tchb0ard
Some issues when combining with certain character LoRAs, about 3/5 success-rate of the ones tested.
1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
