mo-di-diffusion#
README(From Huggingface)#
Mo Di Diffusion
This is the fine-tuned Stable Diffusion 1.5 model trained on screenshots from a popular animation studio. Use the tokens modern disney style in your prompts for the effect.
If you enjoy my work, please consider supporting me
[
Videogame Characters rendered with the model:
Animal Characters rendered with the model:
Cars and Landscapes rendered with the model:
Prompt and settings for Lara Croft:#
modern disney lara croft Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 3940025417, Size: 512x768
Prompt and settings for the Lion:#
modern disney (baby lion) Negative prompt: person human Steps: 50, Sampler: Euler a, CFG scale: 7, Seed: 1355059992, Size: 512x512
This model was trained using the diffusers based dreambooth training by ShivamShrirao using prior-preservation loss and the train-text-encoder flag in 9.000 steps.
🧨 Diffusers#
This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion.
You can also export the model to ONNX, MPS and/or FLAX/JAX.
from diffusers import StableDiffusionPipeline
import paddle
model_id = "nitrosocke/mo-di-diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, dtype=paddle.float16)
pipe = pipe
prompt = "a magical princess with golden hair, modern disney style"
image = pipe(prompt).images[0]
image.save("./magical_princess.png")
Gradio & Colab#
We also support a Gradio Web UI and Colab with Diffusers to run fine-tuned Stable Diffusion models:
[
[
License#
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage. The CreativeML OpenRAIL License specifies:
You can't use the model to deliberately produce nor share illegal or harmful outputs or content
The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully) Please read the full license here
Model Files#
README.md (3.6 KB)
model_index.json (616.0 B)
safety_checker/model_config.json (368.0 B)
safety_checker/model_state.pdparams (1.1 GB)
scheduler/scheduler_config.json (318.0 B)
text_encoder/model_config.json (267.0 B)
text_encoder/model_state.pdparams (469.5 MB)
tokenizer/merges.txt (512.3 KB)
tokenizer/special_tokens_map.json (389.0 B)
tokenizer/tokenizer_config.json (769.0 B)
tokenizer/vocab.json (1.0 MB)
unet/config.json (1.0 KB)
unet/model_state.pdparams (3.2 GB)
vae/config.json (670.0 B)
vae/model_state.pdparams (319.1 MB)