Zum Inhalt springen
ModelAufgelistetExtern
Browse files

Dreamshaper 5 Inpainting

lykon-models/dreamshaper-5-inpainting is a Stable Diffusion Inpainting model that has been fine-tuned on runwayml/stable-diffusion-inpainting.

Quellehuggingface.co/Lykon/dreamshaper-5-inpainting/tree/f7b59bc707ac01c54bb3ba8089d848855e852fab
ArtOtherVersionRevision f7b59bcBBewertung

Modellquelle

Art
Other
Dateigröße
160 MB–3,20 GB
Version
vRevision f7b59bc
Aktualisiert
26. Okt. 2026
Downloads
10
Quelle
Hugging Face

Quellenbeschreibung

Dreamshaper 5 inpainting

lykon-models/dreamshaper-5-inpainting is a Stable Diffusion Inpainting model that has been fine-tuned on runwayml/stable-diffusion-inpainting.

Please consider supporting me:

Diffusers

For more general information on how to run inpainting models with 🧨 Diffusers, see the docs.

  1. Installation
pip install diffusers transformers accelerate
  1. Run
from diffusers import AutoPipelineForInpainting, DEISMultistepScheduler
import torch
from diffusers.utils import load_image

pipe = AutoPipelineForInpainting.from_pretrained('lykon-models/dreamshaper-5-inpainting', torch_dtype=torch.float16, variant="fp16")
pipe.scheduler = DEISMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to("cuda")

img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png"
mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png"

image = load_image(img_url)
mask_image = load_image(mask_url)


prompt = "a majestic tiger sitting on a park bench"

generator = torch.manual_seed(33)
image = pipe(prompt, image=image, mask_image=mask_image, generator=generator, num_inference_steps=25).images[0]  
image.save("./image.png")

Notes

  • Version 8 focuses on improving what V7 started. Might be harder to do photorealism compared to realism focused models, as it might be hard to do anime compared to anime focused models, but it can do both pretty well if you're skilled enough. Check the examples!
  • Version 7 improves lora support, NSFW and realism. If you're interested in "absolute" realism, try AbsoluteReality.
  • Version 6 adds more lora support and more style in general. It should also be better at generating directly at 1024 height (but be careful with it). 6.x are all improvements.
  • Version 5 is the best at photorealism and has noise offset.
  • Version 4 is much better with anime (can do them with no LoRA) and booru tags. It might be harder to control if you're used to caption style, so you might still want to use version 3.31. V4 is also better with eyes at lower resolutions. Overall is like a "fix" of V3 and shouldn't be too much different.

Quellen

1 Quelle
Hugging FacePrimärVersion f7b59bc707ac01c54bb3ba8089d848855e852fab
huggingface.co/Lykon/dreamshaper-5-inpainting/tree/f7b59bc707ac01c54bb3ba8089d848855e852fab

Verifiziert 26. Okt.

Download files

Modellartefakte

8 Artefakte

safety_checker/model.fp16.safetensors

safetensors · 580 MB · SHA-256 57ecdfa243b1…84f6 · Hugging Face

Download file

safety_checker/model.safetensors

safetensors · 1,13 GB · SHA-256 fb351a5ded81…fde8 · Hugging Face

Download file

text_encoder/model.fp16.safetensors

safetensors · 235 MB · SHA-256 446856a4892a…6b98 · Hugging Face

Download file

text_encoder/model.safetensors

safetensors · 469 MB · SHA-256 2791902592b6…f1dc · Hugging Face

Download file

unet/diffusion_pytorch_model.fp16.safetensors

safetensors · 1,60 GB · SHA-256 1a16da50853c…66f4 · Hugging Face

Download file

unet/diffusion_pytorch_model.safetensors

safetensors · 3,20 GB · SHA-256 0f4e50eacca1…1e11 · Hugging Face

Download file

vae/diffusion_pytorch_model.fp16.safetensors

safetensors · 160 MB · SHA-256 3e4c08995484…af9a · Hugging Face

Download file

vae/diffusion_pytorch_model.safetensors

safetensors · 319 MB · SHA-256 2aa1f43011b5…83ec · Hugging Face

Download file

Quellenauszüge

3 Auszüge
Readme8. Aug.huggingface.co/Lykon/dreamshaper-5-inpainting

--- language: - en license: creativeml-openrail-m tags: - stable-diffusion - stable-diffusion-diffusers - inpainting - art - artistic - diffusers - anime - dreamshaper duplicated_from: lykon-models/dreamshaper-5-inpainting --- # Dreamshaper 5 inpainting `lykon-models/dreamshaper-5-inpainting` is a Stable Diffusion Inpainting model that has been fine-tuned on [runwayml/stable-diffusion-inpainting](https://huggingface.co/runwayml/stable-diffusion-inpainting). Please consider supporting me: - on [Patreon](https://www.patreon.com/Lykon275) - or [buy me a coffee](https://snipfeed.co/lykon) ## Diffusers For more general information on how to run inpainting models with 🧨 Diffusers, see [the docs](https://huggingface.co/docs/diffusers/using-diffusers/inpaint). 1. Installation ``` pip install diffusers transformers accelerate ``` 2. Run ```py from diffusers import AutoPipelineForInpainting, DEISMultistepScheduler import torch from diffusers.utils import load_image pipe = AutoPipelineForInpainting.from_pretrained('lykon-models/dreamshaper-5-inpainting', torch_dtype=torch.float16, variant="fp16") pipe.scheduler = DEISMultistepScheduler.from_config(pipe.scheduler.config) pipe = pipe.to("cuda") img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" image = load_image(img_url) mask_image = load_image(mask_url) prompt = "a majestic tiger sitting on a park bench" generator = torch.manual_seed(33) image = pipe(prompt, image=image, mask_image=mask_image, generator=generator, num_inference_steps=25).images[0] image.save("./image.png") ``` ![](./image.png) ## Notes - **Version 8** focuses on improving what V7 started. Might be harder to do photorealism compared to realism focused models, as it might be hard to do anime compared to anime focused models, but it can do both pretty well if you're skilled enough. Check the examples! - **Version 7** improves lora support, NSFW and realism. If you're interested in "absolute" realism, try AbsoluteReality. - **Version 6** adds more lora support and more style in general. It should also be better at generating directly at 1024 height (but be careful with it). 6.x are all improvements. - **Version 5*...

Note26. Okt.huggingface.co/Lykon/dreamshaper-5-inpainting

Source context: 10 downloads · 1 likes · Pipeline image-to-image · Library diffusers · Repo Lykon/dreamshaper-5-inpainting

Note8. Aug.huggingface.co/Lykon/dreamshaper-5-inpainting

Source context: 18 downloads · 1 likes · Pipeline image-to-image · Library diffusers · Repo Lykon/dreamshaper-5-inpainting