by dreamlike-art
Open source · 6k downloads · 1024 likes
Dreamlike Diffusion 1.0 is an image-generation model fine-tuned from Stable Diffusion 1.5, specifically optimized to produce high-quality artistic works. It excels at creating stylized images, whether dreamlike landscapes, portraits, or fantastical illustrations, with a strong focus on detail and aesthetics. To enhance the artistic effect, it is recommended to include the keyword "dreamlikeart" in prompts if the style appears too weak. Available for free via the platform dreamlike.art, it stands out for its ability to generate images in a variety of aspect ratios, suited to both portrait formats (2:3 or 9:16) and landscape formats (3:2 or 16:9), while favoring slightly higher resolutions for crisper results.
Use the same prompts as you would for SD 1.5. Add dreamlikeart if the artstyle is too weak.
Non-square aspect ratios work better for some prompts. If you want a portrait photo, try using a 2:3 or a 9:16 aspect ratio. If you want a landscape photo, try using a 3:2 or a 16:9 aspect ratio.
Use slightly higher resolution for better results: 640x640px, 512x768px, 768x512px, etc.
https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0
You can use this model for free on dreamlike.art!
We support a Gradio Web UI to run dreamlike-diffusion-1.0:
Download dreamlike-diffusion-1.0.ckpt (2.13GB)
This model can be used just like any other Stable Diffusion model. For more information, please have a look at the Stable Diffusion Pipeline.
from diffusers import StableDiffusionPipeline
import torch
model_id = "dreamlike-art/dreamlike-diffusion-1.0"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "dreamlikeart, a grungy woman with rainbow hair, travelling between dimensions, dynamic pose, happy, soft eyes and narrow chin, extreme bokeh, dainty figure, long hair straight down, torn kawaii shirt and baggy jeans, In style of by Jordan Grimmer and greg rutkowski, crisp lines and color, complex background, particles, lines, wind, concept art, sharp focus, vivid colors"
image = pipe(prompt).images[0]
image.save("./result.jpg")
This model is licesed under a modified CreativeML OpenRAIL-M license.