metadata
license: creativeml-openrail-m
language:
- en
base_model: sd-legacy/stable-diffusion-v1-5
pipeline_tag: text-to-image
library_name: diffusers
tags:
- art
- stable-diffusion
- text-to-image
- pokemon
- fine-tuned
- non-commercial
- research
🔬 Research Use | Non-Commercial
📄 License
This model is fine-tuned from sd-legacy/stable-diffusion-v1-5 under CreativeML Open RAIL-M License.
🚀 Usage
from diffusers import StableDiffusionPipeline
pipe = StableDiffusionPipeline.from_pretrained("PPPPPilot/StableDiffusionPokemon")
image = pipe("a cute pokemon character").images[0]
image.save("my_pokemon.png")
✨ Example Display
Input Prompt: "a cute pokemon character"
Input Prompt: "a green color frog pokemon character"
Input Prompt: "a singer pokemon character looks like the American Singer star Taylor Swift"
Input Prompt: "a pokemon character looks like Chinese action movie star Jackie Chan"
Input Prompt: "a US President Donald Trump pokemon character, human-like"
✍🏼 Technical Specification
Dataset: reach-vb/pokemon-blip-captions
Training Steps: 10,000
Evaluation Score: FID 60.20, CLIP 0.235
License: CreativeML Open RAIL-M (Non-commercial)