2000's Emo Art (Pony Diffusion V6 XL)

Prompt
score_9, 2000s emo, long hair, full body, hair over one eye, clothed, white background, hair, shirt, humanoid, choker, female, striped socks, red hair, striped, safe, solo, chibi, simple background, clothing, o_o, undead, 1girl

Prompt
score_9, 2000s emo, solo, long hair, humanoid, female, black hair, smile, solo, clothing, skirt, 1girl, :3, full body, striped clothing, hair, standing, boots, mammal, striped thighhighs, simple background, open mouth, o_o, standing on one leg

Prompt
score_9, 2000s emo, a man in a gray striped shirt waving to the viewer while holding a knife behind his back, full body, male, solo, striped shirt, gray shirt, hair, clothing, humanoid, smiling, waving, holding knife, sharp teeth, o_o

Prompt
score_9, 2000s emo, solo, long hair, humanoid, female, black hair, smile, solo, chibi, clothing, skirt, 1girl, :3, full body, striped clothing, hair, standing, boots, mammal, striped thighhighs, simple background, open mouth, o_o, standing on one leg

This model was originally uploaded on CivitAI, by analogspiderweb. The information below was provided by the author on CivitAI: (CivitAI)

Model description

DISCLAIMER: You may not be able to 100% recreate some of the showcase images.

The training process was a mess and I thought the two models I made were the same. There's no guarantee on whether some images were made with v1 or v2. (v2 is the one available to download)

AI art finally has soul (again).

Prompt format was "score_9, 2000s emo, (put your tags here)"

Trigger words

You should use 2000s emo to trigger the generation.

Download model

Weights for this model are available in Safetensors format. Download them in the Files & versions tab.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

device = "cuda" if torch.cuda.is_available() else "cpu"

pipeline = AutoPipelineForText2Image.from_pretrained('stabilityai/stable-diffusion-xl-base-1.0', torch_dtype=torch.float16).to(device)
pipe.load_lora_weights('analogspiderweb/2000-s-emo-art-pony-diffusion-v6-xl', weight_name='ponydiffusionv6-2000s-emov2.safetensors')
image = pipeline('score_9, 2000s emo, long hair, full body, hair over one eye, clothed, white background, hair, shirt, humanoid, choker, female, striped socks, red hair, striped, safe, solo, chibi, simple background, clothing, o_o, undead, 1girl ').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers