Fares Fares - SD 1.5

Use Lora weight 0.7 to 0.9

Fares Fares (born 29 April 1973) is a great Swedish-Lebanese actor of Assyrian descent. Known for his performances in the video game A Way Out (2018), TV series Westworld (2018), Chernobyl (2019) and The Wheel of Time (2021).

This is the SD 1.5 version. I got good resemblance in my first training version... comparing to SDXL it was way easier (not necessarily better images).

You will get the best results and resemblance with the prompt keyword (Fares Fares:1.3)

Keywords:

Fares Fares

Supporting prompts:

25 years old, 35 years old, 40 years old, 45 years old, 50 years old, medium-length hair, slicked back hair, grease hair, half-open mouth, closed mouth, stubble beard, beard, reading glasses, open-mouthed, side view, profile, front view

Negative supporting prompts:

Low quality, Low rated, jpeg artifacts, dim lit (as there were some pictures with bad quality but captioned as so on the dataset)

Note on keyword: I thought that because his name is a repetition, that only “Fares” would be enough as a keyword, but it is not! As the training data was caption “Fares Fares”, the two words together trigger the best effect.

My Textual Inversion for SD 1.5 was just no good. No acceptable resemblance. Need to try again with different settings maybe, so I wont publish it right now.

Try out my SD 1.5 and TI here (I'll add the link as I upload them):

Fares Fares – Lora SDXL

Fares Fares – TI SDXL (will update later)

The base checkpoint is the realisticVisionV51_v51VAE 3.97GB. I used it instead of the original 1.5 because this is not a broad concept. To get best resemblance you should use the best model for it, so use realistic vision 5.1.

Please use high-res fix to get better results

CFG: 5.5

Clip skip: 1

512px

DPM++ 3M Exponential (50 steps or more)

DPM++ 2M Karras (25 Steps or more)

DPM++ 2S a Karras

I did not tried lora block weights yet, it might be what it is missing to make it perfect. Maybe in the future. 

Want to have some fun? Install wildcards dynamic prompts extension: Here it is a good crafted script I made for xyz pot testing. Paste on prompt and have fun with crazy results:

<lora:Fares_FaresSD15:0.8> {03::profile side view|front view} {0.3::extreme face close-up|0.3::face close-up|medium body shot|far away full body shot} (Fares Fares:1.3) age {50|45|40|35} {on the beach|taking a selfie on a mountain rock|0.5::laying down in bed|wearing a clown costume|wearing a cop uniform|wearing a soccer uniform|wearing open unbuttoned shirt}, {||0.3::pink|0.3::blue|0.3::blond} {short grease hair|medium-length hair|stylish quiff hair|shoulder length long hair|long tied back man bun hair}, {tank top shirt|t-shirt|shirtless|suit}, {long scruffy|(shaved:1.2)|stubble|goatee|mustache only} beard, {happy face|devilish face|laughing|serious face|pouting face|angry face}, natural lighting, {sunlight|0.5::moonlight|0.5::dark dim nigh|0.4::neon city lights}, 4k uhd, dslr, soft light, high quality, Fujifilm XT3

Current problems with the Lora:

• face or body distortions. Use high res fix or try different seed and ratio

Some settings: Trained 768res. 177 pictures. 10 steps for great quality pictures, 5 steps for OK pictures. 2 different folders (sharing the same “Fares Fares person" concept). I still prefer AdamW for SD15.

I should have used some of the CGI pictures from the game "A Way Out" to make it more flexible with nonrealistic results… maybe in a future version.

Hopefully you can leave some results and some comments. Any idea is appreciated. Thank you.