Edit model card

Dracula (Sir Christopher Lee)

Prompt
RAW color photo, ChristopherLee_Dracula , sitting, playing poker, indoors, gaming table, playing cards, Monte Carlo casino, night <lora:ChristopherLee_Dracula_v1:0.75> <lora:XenoDetailer_v2:0.75>
Negative Prompt
(((girl))), (((boy))), (((underage))), (((watermark))), signature, low contrast, underexposed, overexposed
Prompt
Color street poster, Communist bloc political propaganda, Soviet realism, ChristopherLee_Dracula , campaign, running for office, Governor of Transylvania, mass produced, printed on paper, garish colors <lora:ChristopherLee_Dracula_v1:1> <lora:XenoDetailer_v2:0.3>
Negative Prompt
(((girl))), (((boy))), (((underage))), (((watermark))), signature, low contrast, underexposed, overexposed,
Prompt
RAW photo, candid, ChristopherLee_Dracula as Darth Tyranus, holding red lightsaber, pointing at viewer, short white beard, Star Wars cosplay <lora:ChristopherLee_Dracula_v1:0.8> <lora:XenoDetailer_v2:0.7>
Negative Prompt
(((girl))), (((boy))), (((underage))), (((watermark))), signature, low contrast, underexposed, overexposed
Prompt
RAW photo, Close-up, face focus, ChristopherLee_Dracula, vampire, red eyes, fangs:1.2, baring fangs:1.2, hissing, open mouth, blood on chin, Hammer Films, shot by Terence Fisher, horror, inhuman, animal, deadly <lora:ChristopherLee_Dracula_v1:1> <lora:XenoDetailer_v2:0.6>
Negative Prompt
(((girl))), (((boy))), (((underage))), (((watermark))), signature, low contrast, underexposed, overexposed
Prompt
Hand-drawn cel animation, anime, Castlevania on Netflix, candid, full body shot, ChristopherLee_Dracula, vampire, red eyes, fangs:1.2, goatee, open mouth, highly detailed, Frederator Studios, villainous <lora:ChristopherLee_Dracula_v1:0.9> <lora:XenoDetailer_v2:0.1>
Negative Prompt
(((girl))), (((boy))), (((underage))), (((watermark))), signature, low contrast, underexposed, overexposed, realistic
Prompt
RAW photo, candid, ChristopherLee_Dracula as Saruman the White, long white hair, long white beard, white robe, vampire, red eyes, fangs, baring fangs, bloody, Lord of the Rings, Tolkein, shot by Peter Jackson <lora:ChristopherLee_Dracula_v1:0.8> <lora:XenoDetailer_v2:0.6>
Negative Prompt
(((girl))), (((boy))), (((underage))), (((watermark))), signature, low contrast, underexposed, overexposed
Prompt
RAW photo, candid, ChristopherLee_Dracula, working, black cape with red lining, red polo shirt, khakis:1.1, dramatic lighting, indoors, Target retail store, night, vampire, red eyes, fangs, scary, intimidating <lora:ChristopherLee_Dracula_v1:0.9> <lora:XenoDetailer_v2:0.5>
Negative Prompt
(((girl))), (((boy))), (((underage))), (((watermark))), signature, low contrast, underexposed, overexposed

Model description

With all due respect to the OG Bela and Gary Oldman's buttcheek hairstyle, the best Dracula is Hammer Studio's version, played by Sir Christopher Lee. Put some respect on that name!

I did not caption out his normal clothes, and let's face it, he rarely leaves the house, so at a strength of 1 you are going to get pretty vanilla Drac. If you lower it to 0.9 or 0.8, you should be able to get him out of the house and maybe in some different outfits. The nice thing is Stable Diffusion knows who both Christopher Lee and Dracula are, so you may be able to drop the strength quite low in a pinch and still retain his look.

I realized pretty late that his fingers might be screwy. Reach out if you see that. In the movies I have, he rarely holds anything and uses his long fingers to make scary threats, so I may need to purge hand pics from the training set. Possibly a blurry screencap is in there.

About half the images are normal and half vamped out, so use "vampire", "fangs", "red eyes", "baring fangs", and "open mouth" in your prompt to encourage evil, and put the first 3 in your negative prompt if you want the "faking humanity" look.

Fangs are still hard. I noticed using hires fix might make the fangs grow, only to have ADetailer "fix" them shorter, so keep an eye out for that.

Trigger words

You should use ChristopherLee_Dracula to trigger the image generation.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.

Downloads last month
0
Inference Examples
Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Adapter for