KHongJae's picture
Update README.md
7ac2f4a verified
metadata
base_model: KHongJae/full_train_TE_D_0_10000to50000
library_name: diffusers
license: creativeml-openrail-m
tags:
  - text-to-image
  - dreambooth
  - diffusers-training
  - stable-diffusion
  - stable-diffusion-diffusers
inference: true

KHongJae/Chatting_Based_Emoji_Generation_Model

T-Academy ASAC 6๊ธฐ DL ํ”„๋กœ์ ํŠธ์—์„œ ์‚ฌ์šฉํ•œ ์ด๋ชจํ‹ฐ์ฝ˜ ์ƒ์„ฑ ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.
๊ธฐ์กด ๋ฌ˜์‚ฌํ˜• ํ”„๋กฌํ”„ํŠธ์—์„œ๋งŒ ์ž‘๋™ ํ•˜๋˜ Stable Diffusion์„ ๋Œ€ํ™”ํ˜• ํ”„๋กฌํ”„ํŠธ์—์„œ ์ž‘๋™ํ•  ์ˆ˜ ์žˆ๋„๋ก ์‹œ๋„ํ•œ ๋ชจ๋ธ์ž…๋‹ˆ๋‹ค.

Intended uses & limitations

  • prompt : 'ํŒŒ๋ž€ ๊ท€๋ฅผ ๊ฐ€์ง„ ๊ณ ์–‘์ด, ์ด๋ชจํ‹ฐ์ฝ˜, ๋‹จ์ƒ‰ ๋ฐฐ๊ฒฝ, ๋””์ €ํŠธ ๋จน๋Š” ์ค‘!'

img_0 img_1 img_2

How to use

pipeline = DiffusionPipeline.from_pretrained(
  "KHongJae/Chatting_Based_Emoji_Generation_Model",
  torch_dtype=torch.float16
).to("cuda")
pipeline.scheduler = UniPCMultistepScheduler.from_config(pipeline.scheduler.config)
prompt = "Create your own prompt"
negative_prompt = "Create your own negative prompt"

pipeline(
  prompt=prompt,
  negative_prompt=negative_prompt,
  width=200,
  height=200,
  num_inference_steps=50,
  num_images_per_prompt=1
).images[0]

Training details

  • ์นด์นด์˜คํ†ก ์ด๋ชจํ‹ฐ์ฝ˜ ๋ฐ์ดํ„ฐ
  • ChatGPT4