lora_models_inect / README.md
Bjarne12's picture
Update README.md
d15ad17 verified

Activation Words

  • CinematicStyleFlux_v1.safetensors

    • No trigger word needed, but using "cinematic" or "cinematic still image" can help.
    • Trained on landscape images.
  • Sony_Alpha_A7III.safetensors

    • Designed for a sony_a7III professional style photo.
  • Realistic_INKU.safetensors

    • Represents an early 2010s snapshot photo captured with a phone and saved as IMG_2018.CR2.
    • LoRa Strength: 1.0 (only lower as a last resort or when needed, e.g. when combining with other LoRa's).
    • Guidance:
      • Minimum: 2.5 (for more realism)
      • Maximum: 3.5 (for more coherence)
    • Steps: 20, 25, 40, or 50 steps (these seem to be the optimal convergence points).
    • Scheduler Options:
      • euler + ddim_uniform (more realism)
      • OR simple (more coherence)
  • Sinfully_Stylish_1.0_Flux.safetensors

    • Conveys a sinfully stylish vibe with dramatic light, soft light, and long shadows.
    • Use low weights (0.2) and only one trigger word.
  • aeshteticv5.safetensors

    • lora lora to get good asthethic poses.
    • trigger word: aesthetic_pos3, dynamic_pos3
  • UltraRealPhoto_Inect.safetensors

    • Setting i use in ComfyUI for Flux:
    • CFG=1, Guidance =2.5, Scheduler=Beta, Sampler=dpmpp_2m, Steps=40, Strength= from 0.8 to 1.0 works good, but i'm usually use with 1, but if hands getting worse then i set 0.87
  • Kodak Motion Picture Film style v1.safetensors

    • Kodak Motion Picture Film style
    • Analog photography

Artsy_Photo-000027.safetensors

  • Artsy Photo
  • Strength: 0.9

Flux_Skin_Detailer.safetensors

  • Strength: 0.7
  • no activation word