Civit's generator not letting you use a negative value? Use v1.0-negated, which makes it so positive values zoom out!
Zooms in and out on character portraits. I've tried to balance it so that 1.0 is zoomed in close to the character's face, and -1.0 is a full body shot, however, your results may vary depending on your subject and what checkpoint you're using. I've had generally good luck up to +/-1.25 and even more in some cases.
This works with both anime and photorealistic generations. It was trained with humans in mind, and has not been tested with animals or scenery, so YMMV.
Description
FAQ
Comments (22)
great idea, does it work in pony?
Unfortunately, no.
@_Envy_ nope, working. but for "-1" effect need strenght "-6" >.<'
something like that "<lora:d\EnvyZoomSliderXL01:-6>".
Hm civitai doesn't let me go negative on either of these
Like the description says: "Use v1.0-negated, which makes it so positive values zoom out!"
No need to use negative values.
It's limited to 0, can't be lower on site (no idea why, it was working normally some weeks ago)
Amazing, I am curious about how the training data is organized.
does nothing
Are you using it for an SDXL based model?
@haasetomoko203 XL based merges.
if your image is too busy at other places, try combining it with an (((portrait:1.8))) or alike
Are you using this repo? https://github.com/rohitgandikota/sliders
Do you know what parameters I would use to for a Flux zoom slider?
The example for Age is:
target=person and positive=old person and unconditional=young person (opposite of positive) and neutral=person
But not sure what you defined the parameters as for zoom levels?
Negative version can't be used with same models as the normal versions on site
seems like something happened with this, using pony xl and it worked with both versions but now it doesnt even show up when i search for it. wondering if it had be updated to be just SD.
Same for me
same issue here
this happens certain models across SD, SDXL, and PONY, (IL, Flux, and whatever the one i saw today that was a symbol instead of any letters- i dunno as ive only used Flux for a few months and Illustrious for a few days) i dont know why it happens, and why it can only be used on generations by going to the main model page and adding via "Create" or why sometimes it wont even show up in searches, but anytime it does the comment section normally has one person explaining why and that explanation usually is 75% in code but i know it happening to me right now with a few models across different checkpoints but in regards to LORAS
wait are u saying from the "Create" sidebar if you try to add "Additional resources" the model in question isnt among the tons of ones that show up, and can be searched for at the top by name?
@Legend_of_Chavo_G yes i try to add it in cause it really helps with framing poses but it just doesnt show up, when in the past it would
Remixing works, somehow
works great, thanks for this one.. was exactly what i needed, distance to objects or character has been my problem since i started
For me this remains the most important Lora. Without it images fall flat. The lora improves images while also working perfectly to control the zoom.
Details
Files
Available On (2 platforms)
Same model published on other platforms. May have additional downloads or version variants.