
Ladies and gentlemen, gather 'round for a spice-tacular journey back to the '90s with the original queens of girl power – the Spice Girls! Sporty, Scary, Baby, Ginger, and Posh – these ladies taught us that friendship never ends, especially when it involves platform shoes and Union Jack dresses. With dance moves sharper than our attempts to assemble IKEA furniture, they had us zig-a-zig-ah-ing like there was no tomorrow. Forget about Posh's poker face; our faces lit up brighter than Baby Spice's outfits. So, let's spice up your life and revisit the era when girl groups ruled and every problem could be solved with a catchy pop anthem and a touch of glitter! ?✌️?
So... Here's my attempt at capturing the likenesses of each of the 5 members of the Spice Girls back in the 90s. Be aware that for some datasets I'll probably have to use a mixture of pics from around that era and perhaps a few more recent ones, so you should not expect a perfect resemblance. I'll be publishing the TIs periodically, on an individual basis. Let's begin with...
Victoria Beckham (née Victoria Adams):
As Posh Spice, Victoria contributed to the ensemble's distinct personas, embodying sophistication and glamour. Her sleek fashion choices and poised demeanor complemented the group's dynamic, influencing a generation of fans. Post-Spice Girls, Victoria married famous footballer David Beckham and transitioned into a successful career as a fashion designer, further solidifying her impact on both the music and fashion industries. This is how Victoria looked around that era.
Curious about my work process? I have summarized it here.
Do you have a specific idea for a TI in mind? Visit my website and let me know.
Building a good prompt with my TIs
You're obviously free to experiment, but bear in mind that my TIs are trained with a more or less fixed phrasing, that normally starts with:
"photo of EMBEDDING_NAME, a woman"
So I recommend always starting your prompt like that and then building the rest of the prompt from there. For instance, "photo of beautiful (v1cadms:0.99), a woman, perfect hair, (closeup portrait), (modern photo, party strapless dress), 85mm, (analog, cinematic, film grain:1.3), (at a red carpet event), ((detailed eyes)), (color picture:1.1), (looking at viewer)".
Please also note that I'm using the "add detail" LoRA for my example pics. I recommend setting it around 0.5 for best results. CLIP Skip should always be set at 1 when generating pics with this TI.
描述:
135-step TI trained on a dataset of 15 images with these settings.
Curious about my work process? I have summarized it here.
Do you have a specific idea for a TI in mind? Visit my website and let me know.
训练词语: v1cadms
名称: v1cadms.pt
大小 (KB): 25
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success