Text-to-Image
Diffusers
Safetensors
English
StableDiffusionPipeline
art
stable-diffusion
pokemon
fine-tuned
non-commercial
research
Instructions to use PPPPPilot/StableDiffusionPokemon with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use PPPPPilot/StableDiffusionPokemon with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("PPPPPilot/StableDiffusionPokemon", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
| 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 | |
| **π¬ Research Use | Non-Commercial** | |
| ## π License | |
| This model is fine-tuned from [sd-legacy/stable-diffusion-v1-5](https://huggingface.co/sd-legacy/stable-diffusion-v1-5) under CreativeML Open RAIL-M License. | |
| ## π Usage | |
| ```python | |
| from diffusers import StableDiffusionPipeline | |
| pipe = StableDiffusionPipeline.from_pretrained("PPPPPilot/StableDiffusionPokemon") | |
| image = pipe("a cute pokemon character").images[0] | |
| image.save("my_pokemon.png") | |
| ``` | |
| ## β¨ Example Display | |
| <div align="center"> | |
| <img src="https://huggingface.co/PPPPPilot/StableDiffusionPokemon/resolve/main/cute_pokemon.png" width="256" height="256"> | |
| <br/> | |
| <em>Input Prompt: "a cute pokemon character"</em> | |
| <img src="https://huggingface.co/PPPPPilot/StableDiffusionPokemon/resolve/main/green_frog.png" width="256" height="256"> | |
| <br/> | |
| <em>Input Prompt: "a green color frog pokemon character"</em> | |
| <img src="https://huggingface.co/PPPPPilot/StableDiffusionPokemon/resolve/main/singer_talorS.png" width="256" height="256"> | |
| <br/> | |
| <em>Input Prompt: "a singer pokemon character looks like the American Singer star Taylor Swift"</em> | |
| <img src="https://huggingface.co/PPPPPilot/StableDiffusionPokemon/resolve/main/jackie_chan.png" width="256" height="256"> | |
| <br/> | |
| <em>Input Prompt: "a pokemon character looks like Chinese action movie star Jackie Chan"</em> | |
| <img src="https://huggingface.co/PPPPPilot/StableDiffusionPokemon/resolve/main/trump_pokemon.png" width="256" height="256"> | |
| <br/> | |
| <em>Input Prompt: "a US President Donald Trump pokemon character, human-like"</em> | |
| </div> | |
| ## βπΌ 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) | |