Core ML Converted Model

This model was converted to Core ML for use on Apple Silicon devices by following Apple's instructions here.
Provide the model to an app such as Mochi Diffusion to generate images.

split_einsum version is compatible with all compute unit options including Neural Engine.
original version is only compatible with CPU & GPU option.

Redshift Diffusion

This is the fine-tuned Stable Diffusion model trained on high resolution 3D artworks. Use the tokens redshift style in your prompts for the effect.

The name: I used Cinema4D for a very long time as my go-to modeling software and always liked the redshift render it came with. That is why I was very sad to see the bad results base SD has connected with its token. This is my attempt at fixing that and showing my passion for this render engine.

If you enjoy my work and want to test new models before release, please consider supporting me

Characters rendered with the model: Cars and Landscapes rendered with the model:

Prompt and settings for Tony Stark:

(redshift style) robert downey jr as ironman Negative prompt: glasses helmet Steps: 40, Sampler: DPM2 Karras, CFG scale: 7, Seed: 908018284, Size: 512x704

Prompt and settings for the Ford Mustang:

redshift style Ford Mustang Steps: 20, Sampler: DPM2 Karras, CFG scale: 7, Seed: 579593863, Size: 704x512

This model was trained using the diffusers based dreambooth training by ShivamShrirao using prior-preservation loss and the train-text-encoder flag in 11.000 steps.

Gradio

We support a Gradio Web UI run redshift-diffusion:

🧨 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 torch

model_id = "nitrosocke/redshift-diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "redshift style magical princess with golden hair"
image = pipe(prompt).images[0]

image.save("./magical_princess.png")

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