Downloads · 30 days
122
3% of all-time downloads
ItsJayQz/Roy_PopArt_Diffusion
Roy_PopArt_Diffusion is a text-to-image model from ItsJayQz. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
This is a SD1.5 model trained on pop arts made by the one and only Roy Lichenstein (And some other pop arts). The model can only really do portraits, and even then, to get decent looking results, you do have to tinker…
Downloads · 30 days
122
3% of all-time downloads
All-time downloads
4.4K
Public
Parameters
860M
15.2 GB on disk
Likes
21
Public
Click a slice to open those files.
.safetensors7.6 GB · 50%
From the Hugging Face model README
This is a SD1.5 model trained on pop arts made by the one and only Roy Lichenstein (And some other pop arts). The model can only really do portraits, and even then, to get decent looking results, you do have to tinker with the prompt/create more samples. Occasionally, it still makes realistic looking people with pop art background. For the time being, the best thing you can do is to simply adjust the prompt and/or rerun it. There are definitely a lot of things I can do to improve the model, but I haven't got around to doing that. Please check out important informations on the usage of the model down bellow.
To reference the art style, use the token: roypop style
There is already an existing model that uses textual inversion. This is trained using Dreambooth instead, whether or not this method is better, I will let you judge.
We support a Gradio Web UI to run Roy_PopArt_Diffusion:
Portraits

Prompt used: portrait of name in roypop style, digital art, trending on artstation, highly detailed, fine detail, intricate negative: cartoon, 3d, ((disfigured)), ((bad art)), ((deformed)), ((poorly drawn)), ((extra limbs)), blurry Guidance: 8 Steps: 50 using DDIM
I'm not a prompt wizard so you can probably get better results with some tuning.
Disclaimers
License
Responsibilities
Thanks for checking out the model!