civitai.com Open in urlscan Pro
104.18.23.206  Public Scan

Form analysis
0 forms found in the DOM

Text Content

💸
/
Create
Create

Sign In

Create

home

models

images

videos

posts

articles

bounties

events

builds


DREAMSHAPER

45k
849k
29m
2.8k
6.7k

Updated: Feb 1, 2024

base model

animelandscapes3dphotorealisticinpainting+ 14

8
8 LCM
8-inpainting
8-diffusers
7
7-inpainting
7-diffusers
6.31 baked vae
6.31-inpainting
6.31 diffusers
6 baked vae
6.2 baked vae
6-inpainting
6 no vae
6 diffusers
5 baked vae
5 pruned (no vae) - train
5-inpainting
5 baked vae diffusers
4 baked vae
4-inpainting
4 baked vae fp16
4 no vae
4 no vae fp16
3.32 baked vae (clip fix)
3.31 baked vae
3.31-inpainting
3.3
2.52 (safetensors fixed)
2.52 (pruned)
2.52 (initial release)



Remix



👍
337
❤️
325
😂
9
😢
8
0

Remix



👍
279
❤️
241
😂
13
😢
11
0

Remix



👍
100
❤️
77
😂
2
0

Remix



👍
82
❤️
74
😂
1
0

Remix



👍
79
❤️
64
😂
2
😢
3
0

Remix



👍
65
❤️
31
😂
4
0

Remix



👍
49
❤️
38
😂
1
0

Remix



👍
165
❤️
131
😂
5
0

Remix



👍
54
❤️
36
0

Remix



👍
45
❤️
39
😂
2
0

Remix



👍
48
❤️
30
😂
28
0

Remix



👍
68
❤️
56
0

Remix



👍
46
❤️
38
0

Remix



👍
67
❤️
55
😂
13
😢
3
0

Remix



👍
49
❤️
35
0

Remix



👍
57
❤️
60
😂
1
0

Remix



👍
45
❤️
60
😂
2
0

Remix



👍
38
❤️
31
😂
20
0

Images hidden due to mature content settings

Create




Verified: 9 months ago
SafeTensor

Details
Type
Checkpoint Trained
Stats
379.851
28.048.500
Reviews
Overwhelmingly Positive
(4,942)
Uploaded
Jul 29, 2023
Base Model
SD 1.5
Hash
AutoV2
879DB523C3

1 File
Pruned Model fp16 (1.99 GB)
Download
Verified: 9 months ago
SafeTensor

About this version

 * Better at handling Character LoRA

 * Better at photorealism without sacrificing range (can still do art and anime
   pretty well, even if you might have to increase weight)

 * Better at NSFW

Show more
Lykon
Joined Dec 30, 2022
Tip
Follow
214
19k
378k
3.9m

License:
CreativeML Open RAIL-MAddendum

Remix



👍
337
❤️
325
😂
9
😢
8
0

Remix



👍
279
❤️
241
😂
13
😢
11
0

Remix



👍
100
❤️
77
😂
2
0

Remix



👍
82
❤️
74
😂
1
0

Remix



👍
79
❤️
64
😂
2
😢
3
0

Remix



👍
65
❤️
31
😂
4
0

Remix



👍
49
❤️
38
😂
1
0

Remix



👍
165
❤️
131
😂
5
0

Remix



👍
54
❤️
36
0

Remix



👍
45
❤️
39
😂
2
0

Remix



👍
48
❤️
30
😂
28
0

Remix



👍
68
❤️
56
0

Remix



👍
46
❤️
38
0

Remix



👍
67
❤️
55
😂
13
😢
3
0

Remix



👍
49
❤️
35
0

Remix



👍
57
❤️
60
😂
1
0

Remix



👍
45
❤️
60
😂
2
0

Remix



👍
38
❤️
31
😂
20
0

Images hidden due to mature content settings



DREAMSHAPER - V∞!


PLEASE CHECK OUT MY OTHER BASE MODELS, INCLUDING SDXL ONES!

Check the version description below (bottom right) for more info and add a ❤️ to
receive future updates.
Do you like what I do? Consider supporting me on Patreon 🅿️ to get exclusive
tips and tutorials, or feel free to buy me a coffee ☕
🎟️ Commissions on Ko-Fi




JOIN MY DISCORD SERVER

For LCM read the version description.



Available on the following websites with GPU acceleration:

 * Mage.space

 * Sinkin.ai

 * RandomSeed

 * AnimeMaker.ai

 * Rendernet.ai

 * https://tensor.art/u/600303455797521413


Live demo available on HuggingFace (CPU is slow but free).

New Negative Embedding for this: Bad Dream.



MESSAGE FROM THE AUTHOR

Hello hello, my fellow AI Art lovers. Version 8 just released. Did you like the
cover with the ∞ symbol? This version holds a special meaning for me.

DreamShaper started as a model to have an alternative to MidJourney in the open
source world. I didn't like how MJ was handled back when I started and how
closed it was and still is, as well as the lack of freedom it gives to users
compared to SD. Look at all the tools we have now from TIs to LoRA, from
ControlNet to Latent Couple. We can do anything. The purpose of DreamShaper has
always been to make "a better Stable Diffusion", a model capable of doing
everything on its own, to weave dreams.
With SDXL (and, of course, DreamShaper XL 😉) just released, I think the "swiss
knife" type of model is closer then ever. That model architecture is big and
heavy enough to accomplish that the pretty easily. But what about all the
resources built on top of SD1.5? Or all the users that don't have 10GB of vram?
It might just be a bit too early to let go of DreamShaper.

Not before one. Last. Push.

And here it is, I hope you enjoy. And thank you for all the support you've given
me in the recent months.

PS: the primary goal is still towards art and illustrations. Being good at
everything comes second.


Suggested settings:
- I had CLIP skip 2 on some pics, the model works with that too.
- I have ENSD set to 31337, in case you need to reproduce some results, but it
doesn't guarantee it.
- All of them had highres.fix or img2img at higher resolution. Some even have
ADetailer. Careful with that tho, as it tends to make all faces look the same.
- I don't use "restore faces".

For old versions:
- Versions >4 require no LoRA for anime style. For version 3 I suggest to use
one of these LoRA networks at 0.35 weight:
-- https://civitai.com/models/4219 (the girls with glasses or if it says
wanostyle)
-- https://huggingface.co/closertodeath/dpepmkmp/blob/main/last.pt (if it says
mksk style)
-- https://civitai.com/models/4982/anime-screencap-style-lora (not used for any
example but works great).


LCM

Being a distilled model it has lower quality compared to the base one. However
it's MUCH faster and perfect for video and real time applications.

Use it with 5-15 steps, ~2 cfg. IT WORKS ONLY WITH LCM SAMPLER (as of December
2023, Auto1111 requires an external plugin for it).

Comparison with V7 LCM https://civitai.com/posts/951513

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.

 * Results of version 3.32 "clip fix" will vary from the examples (produced on
   3.31, which I personally prefer).

 * I get no money from any generative service, but you can buy me a coffee.

 * You should use 3.32 for mixing, so the clip error doesn't spread.

 * Inpainting models are only for inpaint and outpaint, not txt2img or mixing.
   

Original v1 description:
After a lot of tests I'm finally releasing my mix model. This started as a model
to make good portraits that do not look like cg or photos with heavy filters,
but more like actual paintings. The result is a model capable of doing portraits
like I wanted, but also great backgrounds and anime-style characters. Below you
can find some suggestions, including LoRA networks to make anime style images.

I hope you'll enjoy it as much as I do.


Official HF repository: https://huggingface.co/Lykon/DreamShaper


Show More
SUGGESTED RESOURCES


Checkpoint

DreamShaper XL
15k
351
298k
Checkpoint

AbsoluteReality
14k
106
223k
Checkpoint

3D Animation Diffusion
3.0k
12
25k
Checkpoint

AAM - AnyLoRA Anime Mix - Anime Screencap Style Model
5.6k
36
50k
Checkpoint

AnyLoRA - Checkpoint
17k
86
205k
Checkpoint

Anime Pastel Dream
5.4k
8
37k
Embedding

BadDream + UnrealisticDream (Negative Embeddings)
8.5k
46
244k
LoRA

Add More Details - Detail Enhancer / Tweaker (细节调整) LoRA
16k
37
250k
Embedding

Fast Negative Embedding (+ FastNegativeV2)
10k
26
173k
Checkpoint

NeverEnding Dream (NED)
17k
140
127k



DISCUSSION

Add Comment
androsynth7610
a month ago

Still one of the best if not the best models around. Certainly is for 1.5

0
Belethian
a month ago

Anyone know the prompts to types of panties that this model have? Example, i
have a spreadsheet on excel for orangemix with prompts, hairs, colors, styles,
poses etc...
I'm trying to make images with thong lace panties, but it's very hard, everytime
i get normal panties with lace details... (sorry about my english, it's not my
first language)

Show More
0
drawillusion
2 months ago

This model has been tested and proven to be great for real-life work. 👍

0
IndustrialVectors

a month ago

A question:
Does your training data include a lot of children?
(Not accusatory, just wondering)

Context:

I have been running hundreds of test generations with only one word or
expression each to test the model's biases on multiple concepts. A lot, and I
mean a lot, of tokens will generate photorealistic children pictures. Be
reassured that I never got anything NSFW with those, I actually did not get
anything NSFW in those test runs (which is good because my tokens were not
NSFW).
Therefore I'm wondering if that's a behavior learn in your dataset or inherited
from base models for your training.

Show More
😂
3
6
RW
rwewc177
14 days ago

sometimes it's a little hard to talk to it but the quality is amazing, for
example i couldn't draw a bear and man fighting with each other no matter how
many time i tried, i always draw a man with bear head

Show More
0
orangekiller404
8 days ago

How to use it as a base mold to train Lora? I had an error as size mismatch for
conv_in.weight.

0
catpawz
15 days ago

Is this model still getting updated? Or is the XL version getting all the
attention?

0
VitaminS
21 days ago

The 5.24G version is a folder. How to use it?

1
Load more
See 5 more hidden comments


GALLERY

Add Post
Add Review
Newest
Filters

KH
khachapuri
10 minutes ago - Cross-post

Remix



0






alan160179142
an hour ago - Cross-post

Remix



👍
1
0


















HE
Hello56
18 minutes ago - Cross-post

Remix


0

fredyandraws98193
an hour ago - Cross-post

Remix


0

JH
Jhinthe
an hour ago - Cross-post

Remix


👍
1
0













Orste
an hour ago - Cross-post

Remix


0

alan160179142
an hour ago - Cross-post

Remix



0

















Fracastor
an hour ago - Cross-post

Remix



0





alan160179142
an hour ago - Cross-post

Remix



0


















© Civitai 2024
Join Us 💼
Advertise 📰
Creators
Terms of Service
Privacy
Safety
Newsroom
API
Status
Wiki
Education
Residency
🛟 Support