stable-diffusion stable-diffusion-diffusers text-to-image photorealistic photoreal diffusers

This 1.0 model is OBSOLETE. We've released a new much better 2.0 version!

Check it out here: https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0

<img src="https://huggingface.co/dreamlike-art/dreamlike-photoreal-2.0/resolve/main/preview1.jpg" style="max-width: 800px;" width="100%"/>

Dreamlike Photoreal 1.0 is a photorealistic Stable Diffusion 1.5 model fine tuned on high quality photos, made by dreamlike.art.

Use the same prompts as you would for photorealistic SD 1.5 gens. You can also use danbooru style tags for characters (1girl, brown hair, etc.).
Non-square aspect ratios work better for some prompts. If you want a portrait photo, try using a 3:4 or a 9:16 aspect ratio. If you want a landscape photo, try using a 16:9 aspect ratio.

Examples

<img src="https://huggingface.co/dreamlike-art/dreamlike-photoreal-1.0/resolve/main/preview.jpg" style="max-width: 800px;" width="100%"/>

dreamlike.art

You can use this model for free on dreamlike.art!

<img src="https://huggingface.co/dreamlike-art/dreamlike-photoreal-1.0/resolve/main/dreamlike.jpg" style="max-width: 1000px;" width="100%"/>

CompVis

Download dreamlike-photoreal-1.0.ckpt (2.13GB)

🧨 Diffusers

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-photoreal-1.0"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")

prompt = "caucasian creative man wearing a sweater, sitting, on an icelandic beach"
image = pipe(prompt).images[0]

image.save("./result.jpg")

License

This model is licesed under a modified CreativeML OpenRAIL-M license.