模型简介: PLEASE READ - WORKFLOW BELOW:- This will probably be the LAST UPDATE for the Dragonfruit models, for a while, at least until I am happy enough with my realistic merge (currently WIP), once it's complete, I will probably update Z.5D to v2, or if I discover any new ways or information on merging. Please wait patiently for my next models, completely separate from the Dragonfruit branch! DragonfruitGT v1 (Z v2) - More fantasy, more range in color, better landscapes and more masculine men. ▣ Please use DragonfruitOG v2.0, if you prefer the thicker lines, less detail and simple color pallet. If you have enjoyed this series of models, please leave a rating! Thanks as always! ~~~~~~~~~~~~~~~~~~~~~~~o(* ̄︶ ̄*)o~~~~~~~~~~~~~~~~~~~~~~~ GT v1.0 (Z v2.0): ▣ Better backgrounds ▣ Deeper contrast - more color ▣ Bolder lines ▣ MORE DETAIL -Settings for GT: -Steps: 30-50 -Clip skip: 2 -Upscaler: Euler a / DPM++ 2M SDE Karras -Adetailer extension -VAE: berrysmix ~~~~~~~~~~~~~~~~~~~~~~~o(* ̄︶ ̄*)o~~~~~~~~~~~~~~~~~~~~~~~ 示例提示词和参数: Prompt: masterpiece, best quality, portrait, solo, upper body, looking at viewer, detailed background, detailed face, Bio-spiritualist, nature-connected visionary, solo, serene eyes, ethereal hairstyle made of leaves, earthly hair color, arched eyebrows, organic attire, peaceful expression, verdant forest background, <lora:BioPunkAI:0.2> Negative prompt: lowres, text, error, cropped, worst quality, low quality, jpeg artifacts, out of frame, extra fingers, poorly drawn hands, blurry, too many fingers, long neck, username, watermark, signature, easynegative, ng_deepnegative_v1_75t, verybadimagenegative_v1, By bad artist -neg, Steps: 30, CFG scale: 6, Sampler: Euler a, Seed: 603273425, VAE: BerrysMix.vae, Size: 512x768, Model: dragonfruitGTv1, Parser: Full parser, Script: X/Y/Z grid, X Type: Checkpoint name, Backend: Original, Version: 8ef4aa7, X Values: "dragonfruitGTv1.safetensors [f10e8c54de],dragonfruitZ_v1.safetensors [087b13fb8d],dragonfruitunisex_v2.safetensors [afcf96da04]", "BioPunkAI: b21dfe3791fe", Model hash: f10e8c54de, Operations: "hires, txt2img", Hires steps: 20, Hires upscale: 2, Hires upscaler: RealESRGAN_x4plus_anime_6B, Latent sampler: UniPC, ADetailer model: person_yolov8n-seg.pt, Image CFG Scale: 6, ADetailer version: 23.8.1, Denoising strength: 0.35, ADetailer mask blur: 4, ADetailer model 2nd: face_yolov8n.pt, ADetailer confidence: 0.3, ADetailer dilate/erode: 4, ADetailer mask blur 2nd: 4, ADetailer confidence 2nd: 0.3, ADetailer inpaint padding: 32, ADetailer dilate/erode 2nd: 4, ADetailer denoising strength: 0.25, ADetailer inpaint only masked: True, ADetailer inpaint padding 2nd: 32, ADetailer denoising strength 2nd: 0.25, ADetailer inpaint only masked 2nd: True, Clip skip: 2 |