We are very thankful for our sponsors who made this event possible: Creature Comforts, Dog Gone Gorgeous and Pet Haus.
Adapt pet photo into an artistic rendition
Lol. Using the same actress 11 times is to limit the randomisation of the output, and isolate the prompt variables impact he’s teaching. You really chose to rant about something you know nothing about, and assume things about someone you know nothing about. Repulsive….
Duchien04X4 says:
Z says:
I seriously can’t believe I just read this. You honestly wasted your time to say this? Is this how you think? You have some issues. Please get off the internet and do some self reflection.
Pholo says:
/imagine
Désine moi une bouteille absinthe de Paris une belle bouteille avec la Tour Eiffel
Pholo says:
//imagine
Désine moi une bouteille absinthe de Paris une belle bouteille avec la Tour Eiffel
cheap thunder says:
misogyny. Dude… if it was about a guy you would have nothing to say. misogyny is about a guy making a girl feel less. but apricating her. if this misogyny then all guys should just burn out their eyes….
E says:
Thanks for the tutorial, but why all the misogyny?
“We get Emma Watson 11 out of 10 times. Her name is such a strong effect on the model. I think she’s popular among Stable Diffusion users because she looks decent, young, and consistent across a wide range of scenes. Trust me, we cannot say the same for all actresses, especially the ones who have been active in the 90s or earlier…”
We get Emma Watson because her identity is constantly stolen for pornographic purposes—look up deepfake porn, her identity is stolen more than any other celebrity. And why the 90s reference with the ellipsis? Why rag on women who are 30 years or older? Why are you afraid of older looking women? Emma Watson is 33 years old.
This is useful information, but it’s so discouraging to see misogyny rampant in the AI community.
HawtPokkits says:
This guy gives all the answers to the test, and your biggest issue is he used more women? Well if it helps, the artistic representation of women is a more difficult test to the AI than of men; now, if you want to make it more in your fashion then why don’t you make a few models, LoRA’s or what have you, and develop them in the other direction than complain about the examples in the subject matter.
Andrew says:
My comment was on technical aspect of Stable Diffusion v1.5 model. It has something to do with the timing of training and perhaps bias in training data that she looks exceptionally good among all actresses. I don’t watch deep fake porns so I don’t know how common her identity got stolen. But I think it is irrelevant to why she stands out so well in the model.
nostalgicmathst says:
It’s an effect that multiplies the keyword by 1.1 in the case of ( ) and by .9 in [ ]. For example (dog) is same as (dog:1.1) but shorter, so If you would like more dog increased 10% to the actual value you can just ((dog)) instead of (dog:1.21) and calculate faster. Same concept with [ ], [dog] == (dog:0.9) and also [[dog]] == (dog:0.81)
Jimmi says:
how to transform man photo to a beautiful transwomen? Pls guide
Aib says:
Great tutorials, thanks
Rusty says:
I don’t understand correcty between single, double and triple (), []
SummusArtifex says:
Some of these images were clearly generated by MidJourney and not SD.
Andrew says:
They are all generated with SD.
Jesús Ramírez says:
Whatever AI I use, if I want the photo to start from a photo of me that I upload online, then the result is that the face, height, or everything of the subject of the photo I uploaded always changes. How to NOT change the subject but maybe just the landscape, or clothing?
Andrew says:
This cannot be done with prompt alone. You can use inpainting to change just a part of the image, e.g. clothing and background. https://stable-diffusion-art.com/inpainting_basics/ You will need to train a dreambooth model if you want to generate yourself. https://stable-diffusion-art.com/dreambooth/
Sivaemma says:
I didn’t learn anything from this but my eyes are blessed to see emma watson in this
Halaster says:
Thanks for the reply. Yeah, Inpainting right now is generally how I fix the issue as its easy to handle that way. I just wanted to check if I was missing something or if there was a way to get it to actually associate colors more accurately without requiring the extra steps. Some character or some prompt type I did not know about like an underscore between words or something. Since sometimes the color bleed is really bad, completely altering the entire composition, which makes inpainting a bit more work.
Halaster says:
Is there a way to get colors to follow specific guides, for example, in your prompt when you asked for Blue eyes and a White dress you ended up with blue applying to both the eyes AND the dress, with the dress completely ignoring your specified color. Any time I specify two different colors I can almost never get it to actually do what I want. If I ask for say a purple top and white pants, 90% of the time I will end up with either everything purple, or everything white, or with purple pants and white top instead, doing the opposite of what I asked. On top of that all sorts of other objects in the image will be changed to purple or white. I could say a woman sitting under a waterfall in a white top with purple pants and ill end up with a woman sitting under a purple waterfall, with half the rocks being purple, and a purple top. Even if I specifically group and add weights to things. So a woman sitting under a waterfall in a (purple top), and (white pants:1.4). The colors will STILL almost always ignore what I am specifying. Even if I run a script to test this same prompt across 20 different models of all varieties, it will be messed up in every single model. Am I missing something on how to directly tie the aspect of a color to a specific part of the image? Thanks.
Andrew says:
I think this is a limitation of v1 models. The language model is simply not good enough to deal with the complexity. You can try v2.1 models. Alternatively, make your creation a multi-step process. Correct the color with inpainting.
KlaysMoji says:
Use img2img for that! Draw a crude composition in a drawing software of the things you want colored the way you want, and send it to Stable’s Diffusion’s img2img feature with a strength of like 95. If that doesn’t work, use a strength of 60 to get something awful, then reinsert it again with a strength of 60, over and over, until you get a picture that matches your colors. If you don’t know how to compose it, just get your generation that will be wrong, and crudely paint over the elements with the color that you want them, and do the above steps. I recommend this method over inpainting because all the time img2img gives me better results than whatever I was generating initially, the more times a picture is sent through img2img the better it gets, and you can even change the prompt between passes for best results. Sometimes I get something that leaves me in awe and think “this is it”, because it doesn’t even look like something generated by AI anymore. And I’m talking about sending an image 20 times through img2img, changing prompts, copying over pieces of old generations that were the best (which can be done crudely) and using the next img2img to make them blend in. And, of course, using img2img with different models. SD1.5 isn’t good at composition, anime models like Anything V4 (from dezgo) make great compositions, but then everyone looks the same, but you can send them to img2img to a model like Epic Diffusion and get great output. I’ve been unable to draw certain things no matter what prompts I use, but can produce them in Anything V4 and then use img2img to redraw them in more varied styles, specially, Anything V4 can do good photorealism too, all you need to do is fix the anime face (because once it’s in the picture SD recognizes it even if no prompt will produce it.) As a last tip, if you’re generating cartoons, try adding “by KlaysMoji” at the beginning of your list of artists to give them a nice spin ?
delonk says:
This is an excellent tutorial, thank you for sharing.
One thing I noticed was that when I introduced the negative prompts, the images produced had multiple faces. Emma Watson’s face and head had another Emma Watson face and head on the original one. Some images had two faces and bodies merged/intertwined.
Andrew says:
Hi, it should have more to do with the size of the image. The native resolution of SD v1 is 512×512. It will generate two heads or bodies if you deviates too much from it.
Akisho Parker says:
So thats what it is! I was wondering why when I try and do like a tall 2:3 picture they usually end up with a second torso at the bottom.
ultron5 (@ultron55555) says:
realy good article. Thanks!
Greenfox says:
Thanks for the explanation! I was wondering what () and [] did for the people that are already working with SD a bit longer.
It was clear that it highlighted stuff in positive and negative, but not by how much! Now i know.
Kick Off Event at Ska Brewing!
Join us at Ska Brewing at 4pm on Saturday, March 4th to kick off the Powder Hounds Snowboard Art Auction! You will meet the artists, view all 17 boards and place your bids! Come and grab a craft brew, seltzer or non-alcoholic beverage, order some delicious food the Container, listen to live music and enjoy local art, helping local animals.
The Powder Pets Photo Contest was created in partnership with our Powder Hounds Online Art Auction . The art auction features snowboard art created by local artists and placed up for auction in a week long online silent auction. We understand that not everyone is interested in bidding on snowboards or playing the auction game, so we created a fun, interactive, pet friendly photo contest for all to join!
100% of the proceeds from both the photo contest and the art auction will benefit the homeless animals in our care. Funds raised will help us to continue to provide important medical and behavioral care, emergency surgeries, spay & neuter services, vaccinations, free courtesy hold for individuals in need, animal transportation services, supplies and low cost medical services to the community.
Enter your vote for your favorite powder pet! The photo contest runs from Saturday, March 4th – Sunday, March 11th ending at 11:59 p.m. (MT)
Prizes
First Place (valued at $2,000) – The pet voted Durango’s Powder Hound will receive:
- A custom commission snowboard art piece featuring the winning pet, created by internationally collected artist
Ray Phillips . - Creature Comforts gift basket
- pranaDOGS Canine Behavior Assessment. Includes 90-minute in-person session and 2 virtual follow-up sessions. Valued at $145
- Sculpture entitled “Belly Rub, Please” by Durango sculptor, Suzie Grimm
Bio and Gallery Information:
Artist Ray Phillips has always held a passion for creating art. Like many artists, Ray’s artistic journey began as a young child. At age 10 he enrolled at the prestigious Houston Museum of Fine Art School now the Glassell School of Art. As an adult, Ray focused his artistic attention on graphic design and music; playing in a band at night and crafting ad campaigns, posters, t-shirts, logos and branding by day. Ray soon rose to become a partner/creative director at a design and marketing firm in Houston, Texas; yet the longing to create fine art was still present. Ray began his painting career in his free time, integrating skills and techniques he learned as a designer. His work has evolved into an amalgam of typography, abstract composition, collage/mixed media and hidden messages. Each piece is initiated in Ray’s mind and translated to canvas – as much an intellectual pursuit as creative endeavor. Ray is an internationally collected artist with representation in fine art galleries in Vail, Aspen, Telluride, Houston, Austin and Dallas, as well as Canada and Mexico. Read more at rayphillips.com .
Gallery Representation:
- Vail Village Arts Vail, CO
- Vickers Collection – Aspen, CO
- Laura Rathe Fine Art – Dallas, TX
- Laura Rathe Fine Art – Houston, TX
- Lux Perpetua – Merida, MX
- Mixx Projects – Telluride, CO
- Russell Collection – Austin, TX
- Sopa Fine Arts – Kelowna, BC
“Belly Rub, Please” sculpture by Suzie Grimm
Second Place – The dog with the second highest amount of votes will receive:
- One Round of Golf for Four (4) Persons at Glacier Valley Golf Course (includes cart fees), a $100 gift card to use in the pro shop, and a $100 gift card to Glacier’s Mineshaft Bar & Grill (graciously gifted by Glacier Club)!
- Creature Comforts gift basket
- pranaDOGS Canine Behavior Assessment. Includes 90-minute in-person session and 2 virtual follow-up sessions. Valued at $145
Third Place – The dog with the third highest amount of votes will receive:
- LPCHS merch basket. Valued at $200
- Creature Comforts gift certificate .
- pranaDOGS Canine Behavior Assessment. Includes 90-minute in-person session and 2 virtual follow-up sessions. Valued at $145
Don’t forget to check out all the snowboard art up for auction. Click here to view all boards up for auction and place your bids online or “buy it now” before 12:00 p.m. (MT) Sunday, March 14, 2021. 100% of the proceeds benefit the homeless pets in La Plata County!
The Powder Hounds Story
In the fall of 2018, Ray Phillips and his wife Wendy stopped by the Humane Society to drop off donations to our Thrift Store. Of course being animal lovers, they couldn’t leave without saying “hi” and playing with the dogs in our yard. Both were blown away by how much fun the dogs were having, and the dedication of the volunteers working with the dogs. They looked at each and asked, “what can we do to help?”. Driving back home, Ray and Wendy began to scheme ideas, Ray a prolific artist; represented in galleries across the US, Canada and Mexico, along with Wendy a freelance photographer and an avid skier with a resume of volunteer fundraising experiences knew there was something they could do. That’s when the idea for “Powder Hounds Art Auction” was born!
Goal: Enlist artists to hand paint, screen print, carve or decorate used snowboards. Exhibit boards in and around the city of Durango, CO for a month long on-going silent auction, where the public can view and bid on boards. 100% proceeds from the Powder Hounds Art Auction will be donated to La Plata County Humane Society (LPCHS)
Auction: Powder Hounds Art Auction is a two-week long on-going silent auction of snowboard art by artists Place your bid on online. Boards begin at a minimum bid of $100 and 100% of the proceeds will benefit LPCHS. Not a fan of the auction game? “Buy it Now” pricing is available for each board! Winning bids will go to the highest bidder on each board and will be announced at the closing of the silent auction at 11:59 .m. MT on Saturday, March 11th!
TransLink takes next step in Burnaby Mountain gondola proposal
TransLink is asking Metro Vancouver residents to answer a short survey on its plan to install a gondola up Burnaby Mountain to Simon Fraser University.
The questionnaire needs to be completed by Nov. 19, at which point TransLink can ask the Mayors’ Council on Regional Transportation to continue exploring the unapproved project.
Article content
The survey doesn’t state how much the project is expected to cost, but the most recent business plan puts the cost at around $210 million.
Advertisement 2
Story continues below
This advertisement has not loaded yet, but your article continues below.
THIS CONTENT IS RESERVED FOR SUBSCRIBERS ONLY
Subscribe now to read the latest news in your city and across Canada.
- Unlimited online access to articles from across Canada with one account.
- Get exclusive access to the Vancouver Sun ePaper, an electronic replica of the print edition that you can share, download and comment on.
- Enjoy insights and behind-the-scenes analysis from our award-winning journalists.
- Support local journalists and the next generation of journalists.
- Daily puzzles including the New York Times Crossword.
SUBSCRIBE TO UNLOCK MORE ARTICLES
Subscribe now to read the latest news in your city and across Canada.
- Unlimited online access to articles from across Canada with one account.
- Get exclusive access to the Vancouver Sun ePaper, an electronic replica of the print edition that you can share, download and comment on.
- Enjoy insights and behind-the-scenes analysis from our award-winning journalists.
- Support local journalists and the next generation of journalists.
- Daily puzzles including the New York Times Crossword.
REGISTER TO UNLOCK MORE ARTICLES
Create an account or sign in to continue with your reading experience.
- Access articles from across Canada with one account.
- Share your thoughts and join the conversation in the comments.
- Enjoy additional articles per month.
- Get email updates from your favourite authors.
Don’t have an account? Create Account
If you are a Home delivery print subscriber, unlimited online access is included in your subscription. Activate your Online Access Now
Article content
The gondola is part of the mayors’ council’s 10-year plan and has support from the City of Burnaby.
Once the survey is complete, the mayors’ council can approve a business plan and then secure project financing. At that point, if TransLink still wants to go ahead, then the ambitious project can proceed.
The proposed route is from the Production Way Millennium Line Station uphill to the SFU campus. The gondola — which would be similar to the Whistler to Blackcomb Peak to Peak operation — could carry up to 25,000 passengers a day.
Bookmark our website and support our journalism: Don’t miss the news you need to know — add VancouverSun.com and TheProvince.com to your bookmarks and sign up for our newsletters here.
You can also support our journalism by becoming a digital subscriber: For just $14 a month, you can get unlimited, ad-lite access to The Vancouver Sun, The Province, National Post and 13 other Canadian news sites. Support us by subscribing today: The Vancouver Sun | The Province.
Article content
Share this article in your social network
Share this Story : TransLink takes next step in Burnaby Mountain gondola proposal
Comments
Postmedia is committed to maintaining a lively but civil forum for discussion and encourage all readers to share their views on our articles. Comments may take up to an hour for moderation before appearing on the site. We ask you to keep your comments relevant and respectful. We have enabled email notifications—you will now receive an email if you receive a reply to your comment, there is an update to a comment thread you follow or if a user you follow comments. Visit our Community Guidelines for more information and details on how to adjust your email settings.
SHARE YOUR THOUGHTS
To contribute to the conversation, you need to be logged in. If you are not yet registered, create your account now – it’s FREE.
