(redpinkretro) (2024)
Image description: A futuristic, sci-fi setting with a central, dramatic focus on a glowing, fiery sword. The sword is black and engulfed in intense, orange flames. The background features advanced control panels and screens, with a predominantly black and red color scheme, enhancing the high-tech atmosphere. The lighting is dim, with the fiery sword illuminating its immediate surroundings with an orange glow.
Full Generation Parameters:
Octane render portraying a burning machine-greatsword containing the essence of dark entities displayed on a pedestal. Set in a mystical scifi space station, attached to an array of consoles. Paralyzing horror is lingering in the air; color theme black, white, red, fine details, high contrast, vibrant
Steps: 30, CFG scale: 3.5, Sampler: deis_beta, Seed: 134216, Size: 832x1216, Model: flux_unet_jibMixFlux_v61RealPixFixed, Version: ComfyUI, Model hash: 6ffe6182fd
What model do you use to generate the descriptions?
The descriptions are heavily edited JoyCaption Alpha Two descriptions.
Thank you
It gets a lot of things wrong, so you have to do a lot of corrections. It’s impressive how well VLM captioned models work if they’re trained on raw generated captions.