Join Our Discord (900+ Members)

Van Gogh Diffusion

This AI model is a deep learning-based method for creating art in the style of the famous painter, Vincent Van Gogh. It uses a diffusion-based approach to capture the essence of Van Gogh's work and create new images in his style. The model can also be used to transfer an existing image into the same style.

Van Gogh Diffusion

v2 - fixed and working

This is a fine-tuned Stable Diffusion model (based on v1.5) trained on screenshots from the film Loving Vincent. Use the token lvngvncnt at the BEGINNING of your prompts to use the style (e.g., “lvngvncnt, beautiful woman at sunset”). This model works best with the Euler sampler (NOT Euler_a).

Download the ckpt file from “files and versions” tab into the stable diffusion models folder of your web-ui of choice.

If you get too many yellow faces or you dont like the strong blue bias, simply put them in the negative prompt (e.g., “Yellow face, blue”).

Characters rendered with this model: Character Samples prompt and settings used: lvngvncnt, [person], highly detailed | Steps: 25, Sampler: Euler, CFG scale: 6

Landscapes/miscellaneous rendered with this model: Landscape Samples prompt and settings used: lvngvncnt, [subject/setting], highly detailed | Steps: 25, Sampler: Euler, CFG scale: 6

This model was trained with Dreambooth, using TheLastBen colab notebook

🧨 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 = "dallinmackay/Van-Gogh-diffusion"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "lvngvncnt, beautiful woman at sunset"
image = pipe(prompt).images[0]

image.save("./sunset.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:

  1. You can’t use the model to deliberately produce nor share illegal or harmful outputs or content
  2. 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
  3. 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

Become A Patreon

Follow AI Models on Google News

An easy & free way to support AI Models is to follow our google news feed! More followers will help us reach a wider audience!

Google News: AI Models

Related Posts

BurnaBoy RVC Model AI Voice

BurnaBoy RVC Model AI Voice

Introducing the groundbreaking collection of songs by AI BurnaBoy! Produced using VITS Retrieval based Voice Conversion methods, this collection features a range of styles and languages to showcase the model’s capabilities.

Portuguese male TTS Model vits Encoding Trained on cv Dataset at 22050Hz

Portuguese male TTS Model vits Encoding Trained on cv Dataset at 22050Hz

Portuguese (português) male text-to-speech model trained at 22050 Hz and is available to synthesize the Portuguese language.

Bill Wurtz RVC Model AI Voice

Bill Wurtz RVC Model AI Voice

Introducing the groundbreaking Ai Bill Wurtz collection! This compilation of tracks features cutting-edge AI technology, with vocals replaced using top-of-the-line VITS Retrieval based Voice Conversion models.