Last updated 08-11-2026
Category:
Reviews:
Join thousands of AI enthusiasts in the World of AI!
mo-di-diffusion on Hugging Face
mo-di-diffusion is a fine-tuned Stable Diffusion 1.5 checkpoint on Hugging Face that renders characters and scenes in a modern animated-film look. Creator nitrosocke trained it on screenshots from a popular animation studio using DreamBooth with prior-preservation loss and text-encoder training over 9,000 steps. Add the token modern disney style to your prompt to trigger the aesthetic.
General SD 1.5 checkpoints aim for photorealism or broad illustration styles. mo-di-diffusion narrows hard on that glossy character-animation look, which is why sample prompts for game heroes, animals, and landscapes all lean cinematic rather than photographic. The weights load through the standard Diffusers StableDiffusionPipeline, so you can run it locally, in Colab, or inside Hugging Face Spaces without a proprietary API.
Artists, hobbyists, and developers experimenting with character concepts use mo-di-diffusion when they want Disney-adjacent renders without commissioning custom model training. The model card ships Python sample code, links to Gradio demos, and notes ONNX, MPS, and FLAX export options. It is free to download under the CreativeML OpenRAIL-M license with commercial use allowed subject to the license harm restrictions.
Fine-tuned Stable Diffusion 1.5 weights trained with DreamBooth over 9,000 steps
Trigger token modern disney style activates the animation-studio aesthetic
Loads through Hugging Face Diffusers StableDiffusionPipeline with sample Python code
CreativeML OpenRAIL-M license permits commercial redistribution with use restrictions
957 community likes and about 1,175 downloads per month on the model page
Compatible with Gradio Spaces, Colab notebooks, and ONNX, MPS, or FLAX exports
Sample prompts document CFG scale 7, Euler a sampler, and 512px output sizes
Distinct modern animation look from a single prompt token without custom training.
Standard Diffusers integration works in local scripts, Colab, and Hugging Face Spaces.
OpenRAIL-M license allows commercial projects when restrictions are followed.
Model card includes tested sampler settings and negative prompt examples.
Requires your own GPU infrastructure; Hugging Face does not host a default inference endpoint.
Fixed 512px sample sizes in documentation may need upscaling for print work.
Style is narrowly tuned to animation aesthetics and can look off on unrelated subjects.
What is mo-di-diffusion?
mo-di-diffusion is a Hugging Face text-to-image model fine-tuned from Stable Diffusion 1.5 by nitrosocke. It produces images in a modern animated-film style when you include the modern disney style token in your prompt.
Which sampler settings work for mo-di-diffusion?
mo-di-diffusion sample prompts on the model card use 50 steps, Euler a sampler, CFG scale 7, and 512px output sizes. Example seeds and negative prompts are documented for character and animal renders.
What prompt token does mo-di-diffusion need?
mo-di-diffusion expects the phrase modern disney style in your prompt to activate the trained aesthetic. The model card shows example prompts for characters, animals, and landscapes using that token.
Is mo-di-diffusion free?
Yes. mo-di-diffusion is an open-access Hugging Face model you can download and run locally. There is no subscription or per-image fee on the model page itself.
Can mo-di-diffusion be used commercially?
mo-di-diffusion is released under the CreativeML OpenRAIL-M license, which allows commercial use and redistribution of the weights when you pass the same usage restrictions to downstream users.
What hardware does mo-di-diffusion require?
mo-di-diffusion sample code targets CUDA GPUs via torch.float16 inference. The model card also notes ONNX, MPS, and FLAX export paths for other runtimes.