Scarlett Johansson [LORA][Enhancer] (Patreon)

An Enhancer/Helper for me its a LORA that usually sums the weight matching my keywords with the base checkpoint trained keywords, so this LORA was trained with 288 images of Scarlett Johansson but also uses the keyword to match the weight on any specific checkpoints that already contains a Scarlett Johansson on it, so it will act as a multiplier to spot perfect likeness Scarlett Johansson renders just like I did it with Britney Spears.

Trigger Keyword(s):

scarlettjohansson-smf

Prompt example to use it:Prompt:masterpiece, best quality, cinematic, volumetric lighting, very detailed, high resolution, sharp, sharp image, 4k, 8k, 35 mm, <lora:ScarlettJohansson_smf_lora_v3:0.9>, 1girl, scarlettjohansson-smf holding a cup of wine wearing a gorgeous dress on a end year party, blonde hair, jewelry, long hair, lips, earrings, smile, drinks, night, (fireworks:1.3), outdoors, (surrounded by lot of people:1.2), holding wine, <lora:add_detail:0.3>

Negative prompt:EasyNegative, bad-hands-5, badhandv4, text, watermark, low quality, medium quality, blurry, censored, deformed, mutated, anime, toon, render, 3d, illustration, moles, dark skin spots, tattoos, extra fingers

--------------------------------------------

Sharing Epoch:

5 [ ScarlettJohansson_smf_lora_v3.safetensors ]

Recommendations and Specifications:

Sampling Steps: 25

GF SCALE : 7

Checkpoint Recommended: ANY Checkpoint :)

Embeddings used on some Examples:

EasyNegative

bad-hands-5

badhandv4

Enhancers Used:

add_detail.safetensors

ADetailer for this model it's required on low res (512x768) full body or mid body renders to maximize quality. for Portraits it's not really needed but I always use it to do face corrections.[ https://github.com/Bing-su/adetailer.git ]Images rendered using the next checkpoint(s):

Realistic Vision V5.1 - V5.1 (VAE)

Photon V1