Create

Kyle Hyde

LORA
Original


Updated:

blur image
photo of the detective "Kyle Hyde" from Hotel Dusk games, detective, film grain, cinematic film still, 8k hd, portrait,kyle_hyde
  • photo of the detective "Kyle Hyde" from Hotel Dusk games, detective, film grain, cinematic film still, 8k hd, portrait,kyle_hyde
  • Kyle Hyde, detective, (masterpiece, best quality, ultra-detailed, best shadow), cinematic film still, from side, photo of a man in formal attire, holding and talking on phone, in an office, male focus, solo, noir movie,kyle_hyde
  • Kyle Hyde, detective, (masterpiece, best quality, ultra-detailed, best shadow), cinematic film still, photo of a man in formal attire, holding phone and talking on phone, in an office, male focus, solo, 90s detective movie,kyle_hyde
  • Kyle Hyde, (masterpiece, best quality, ultra-detailed, best shadow), cinematic film still, photo of a man wearing a high tech scifi armor, mecha armor, male focus, armor, solo, cape, looking at viewer, blurry background, power armor, knee protection, standing, brown hair, science fiction  ,kyle_hyde
  • Extreme detailed,Realistic,solo, official art, extremely detailed, Extreme Realistic, man, handsome detective, manly, detailed eyes, detailed fine nose, detailed fingers,sleek body, wearing a blue jacket and collared shirt, high quality, Extremely Realistic,kyle_hyde
  • Kyle Hyde portrait, detective, Create a modern-styled sketch portrait in silk textured paper of a handsome man inspired by mix colors roses and love, utilizing the vibrant color palettes and sleek lines reminiscent of the works by Chinese contemporary artist Zhang Xiaogang, background is full of roses abstracts,xxmix_girl,kyle_hyde
  • masterpiece, best quality, (extremely detailed CG unity 8k wallpaper, masterpiece, best quality, ultra-detailed, best shadow), (detailed background), (beautiful detailed face, beautiful detailed eyes), High contrast, (best illumination, an extremely delicate and beautiful),1man,((colourful paint splashes on transparent background, dulux,)), ((caustic)), dynamic angle,beautiful detailed glow,full body,man, detective,kyle_hyde
  • Kyle Hyde, man, detective, solo, male focus, realistic image, from front, walking towards viewer, in a city street, formal attire,kyle_hyde
  • handsome man enjoying nature in village,masculine, mysterious, charming,wearing formal attire ,inst4 style,aesthetic portrait,kyle_hyde
  • Kyle Hyde, mature adult male detective, solo, looking at horizon, realistic, 8k, handsome, male focus, masculine, piercing, portrait,full body, eye focus,raidenshogundef,High detailed,kyle_hyde
  • handsome,ikemen,Slender and muscular,abs,abstract background,
masterpiece, best quality,aesthetic,kyle_hyde
  • Kyle Hyde, a handsome detective man, exuding freedom among white and sky-blue auroras. Incorporate 'Echoing Vortexia' style cosmic ray textures and glowing magnetar plasma body markings. Aim for a Chemiluminescent Impressionism feel,kyle_hyde
  • Kyle Hyde, detective, hansome man, surrounded my mystery, scene from a detective tv show, investigating and thinking, formal black suit and white collared shirt, Aim for a Chemiluminescent Impressionism feel,kyle_hyde

Trigger word: kyle_hyde

Character model of Kyle Hyde from Hotel Dusk and Last Window.

After some testing, both SD 1.5 versions seem to be working fairly well. Mature Male Mix gives some good results from what you can see in the showcase images, but other popular checkpoints also work well.

You might need to include tags such as "masterpiece, best quality etc." in your prompt especially for version E16.

Version E16 (SD 1.5): I used 16 images X 10 repeats X 16 epochs / 2 batch sizes = 1280 steps.

The dataset used for training this model included some sketches / pencil drawings and a few images of lower resolution.

Version E20 (SD 1.5): I used 10 images X 10 repeats X 20 epochs / 2 batch sizes = 1000 steps

In this version I used less images of a better quality, and less black-and-white drawings.

SDXL 1.0 version: trained directly on civitai, with a dataset containing 20 images and updated tags: 20 images X 10 repeats X 10 epochs / 2 batch sizes = 1000 steps.

I need to do more testing but maybe because I included more images (including some of lower resolution) or because I modified the tags, the model seems less reliable in producing high quality results. Plus instead of realistic images it still keeps the pencil drawing style most of the times. It does seem to work better with some checkpoints though - check out the showcase images. Let me know if you can manage to make it work well and consistent.

SDXL E6 version: trained with Tensor Art's online training, with Animagine XL. Updated tags, used only 18 upscaled images of higher resolution: 18 images X 20 repeats, X 6th epoch = 2.160 steps.

SDXL E10 version: same as previous, only it's the 10th epoch (3.600 steps).

SDXL E6 and SDXL10 might be a little under-baked as the character doesn't really look that much as Kyle Hyde sometimes, but it might be better for realistic images. From initial tests, they don't seem to create good results for anime images (they seem to be in a "blurry pencil" style like the one in the showcase).

Civitai link: https://civitai.com/models/277364

508
Runs
1
Downloads
Uploaded
Base ModelSDXL 1.0
Steps1000
Epoch10
Trigger Words
Trained on SDXL 1.0 on civitai, with 20 images in the dataset and updated tags.
  • Download the model file

  • Use without crediting

  • Share merges of this model

  • Use different permissions on merges

Commercial use: None

Comments

Related Posts