<h3 id="please-donate-buzz-for-flux-lora-training-!-vsur4rdu4">Please Donate Buzz for FLUX Lora Training !</h3><h3 id="flux-v1.0-:-kwzmwxbda">FLUX v1.0 :</h3>Trained on FLUX dev with 70 photos of Evangeline Lilly with detailed GPT-4 captions. Tested on FLUX <a target="_blank" rel="ugc" href="http://1.dev">1.dev</a> (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.8-1.0. No keywords needed! Distilled CFG around 1-4 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:Positive : {Artstyle, Character and scene description in usual FLUX fashion}, &lt;lora:Evangeline_Lilly_FLUX_v1-000061:1&gt;<h3 id="sdxl-v3.0-:-akanc514r">SDXL v3.0 :</h3>Trained on Juggernaut X with 240 photos of Evangeline Lilly . Tested on Juggernaut X, Juggernaut v7, RealismEngine 2, RealVisXL3, AlbedoBaseV2! Use with keyword : "evxlilly" . Use around strength 1.0-1.1. CFG 5.0-7.0. Clipskip 1. Can be used for example as follows:Positive : {Artstyle}, {Character and scene description}, evxlilly, &lt;lora:evlilly_juggerX_xl_1_wocap_merger_57_99_144_03_015_055_04_107_06-evxlilly:1.05&gt;Negative : ugly, deformed, airbrushed, photoshop, rendered, (multiple people), child<h3 id="sdxl-v2.0-160mb-:-1z95pv2if">SDXL v2.0 160mb :</h3>Trained on 150 photos of Evangeline Lilly on SDXL 1.0 base with better Lora presets. Less than half the size of the previous version. Use with keyword : "evxlilly"! Lora strength with prompt should be around 1.0. Following prompt structure on Juggernaut v7, realismEngine 2.0 or Juggernautv9 lightning works well:positive : {art style}, {character descrioption and action},evxlilly, &lt;lora:evlilly_32_small_xl_5_standard_wo_cap-merger_24_65_045_055_and_19_30_65_05_02_03-evxlilly:1&gt;negative : photoshop, rendered, (multiple people), blurry, child<h3 id="sdxl-v1.0:-dioufrh2m">SDXL v1.0:</h3>LoRa of Evangeline Lilly trained on 200 images of her with the SDXL base model. Recommended strength of 0.9-1.1 for ComfyUi Lora. The dataset is biased to her smiling so a negative prompt such as (smile:0.6) or so could help reduce this if unwanted.

Evangeline Lilly Face (FLUX + SDXL)

Evangeline_Lilly_FLUX_v1-000061.safetensors

FLUX v1.0

SDXL v3.0

SDXL v2.0 160mb

SDXL v1.0

Evangeline Lilly

 Sexy Girl Snow Killer

- Ashley Artist - # Basic algorithm : FLUX.1* Parameters- Steps: 30- CFG Scale: 3.5- CFG: 0.7- Sampling: Euler The image depicts a person who appears to be a female model set in a wintry urban scene. She is posed against a blue-toned background that resembles an icy snowflake backdrop, suggesting a cold or chilly setting. The lighting is moody and dramatic, possibly artificially enhanced, creating a striking contrast with the subject's skin. The model is dressed in a half-dressed, half-undressed attire. She is wearing a high-visibility white jacket that covers her shoulders and lower part of her body, paired with a low-cut white lace or mesh bra that leaves the upper portion of her body exposed. Adding to her outfit, she has on black leather gloves, which contrast with her skin tone and the bright jacket. A silver sword is held in her left hand, pointing diagonally across her body, indicating a potential action or pose she is taking. Her hairstyle, a messy, high half-up, half-down bun, adds to her style, which appears to be a mix of edgy and alluring

Files with SHA256: 3ca4d8551aae9587205d4c57318e85c2658fd2388848724cb734b0636f57086d