Posts
Search Results
Creative Corner » taggers that support NL? » Post 2
@Bendy and Boney
Thanks and sure! :D
Thanks and sure! :D
Creative Corner » taggers that support NL? » Post 1
only one i can think of off the top of my head is this
https://github.com/fpgaminer/joycaption
https://github.com/fpgaminer/joycaption
anyway, a lora of that sort is also something i’m interested in doing.
maybe we could try and work together?
maybe we could try and work together?
Creative Corner » LoRA - Characters » Post 87
https://civitai.red/models/2656426/my-little-ponymane-sixequestria-girls, I don’t know who will be interested in this LoRA, but it has the entire G4 six.
Creative Corner » Should I keep making LoRAs, or not? Or are my LoRAs complete garbage » Post 7
@Cypher
ayyyyyy you’re back? awesome!
ayyyyyy you’re back? awesome!
Creative Corner » Should I keep making LoRAs, or not? Or are my LoRAs complete garbage » Post 5
It helps when you realize that the people who do stuff like are basically wasting their life spewing hatred online and are likely either
A) Miserable people
B) Bots run by miserable people
B) Bots run by miserable people
The best thing to do is just block and move on. There’s a weird, self-harm mindset some people have where they feel they should not block users because it’s somehow ‘rude’, but it’s not rude to block someone who is actively making your life worse. (Note: I have no idea if Civit even has a block user function).
Regarding your LoRAs, I use many of them and I think they’re great! But the most important thing is yourself, and if hosting on Civit is giving you anxiety / stress, your best bet is to find some alternative method of distribution. HuggingFace has terrible searching tools, but you can upload and distribute LoRAs from there, so if you linked them from here on the Character LoRAs section, people who want to find them could find them through the links here on Tantabus.
An extreme alternative is that you could take the route that most online personalities have to adopt as they grow: put a buffer between yourself and the toxicity. Have someone else manage your affairs while you simply create. It might be a close friend, a girlfriend/boyfriend, or a trusted online friend.
- Create your LoRAs
- Pass them to your ‘buffer’ contact
- Make more LoRAs
Your ‘buffer’ partner
- Takes your LoRAs and uploads them
- Manages comments and DMs silently, and forwards you constructive or positive feedback without telling you about the harassment
Admittedly, this is far easier to write down the steps for than to find a good partnership to work with, especially in an unpaid context, and you need a partner who is going to be able to ignore, for example, threats from anonymous online people. And of course, all of the insinuations of content that can/shouldn’t/should be made with your LoRAs, which is an unfortunate side effect of AI being… well… AI.
Creative Corner » Should I keep making LoRAs, or not? Or are my LoRAs complete garbage » Post 4
@CappyAdams
The only model is NoobAI. I don’t understand how to train it
The only model is NoobAI. I don’t understand how to train it
Creative Corner » Should I keep making LoRAs, or not? Or are my LoRAs complete garbage » Post 3
@Cypher
ah, I’m so sorry to hear that… I hope this isn’t an issue to ask but are you planning on uploading your loras to google drive and sharing the link here or anythin? I’d love to try them out :>
ah, I’m so sorry to hear that… I hope this isn’t an issue to ask but are you planning on uploading your loras to google drive and sharing the link here or anythin? I’d love to try them out :>
Creative Corner » taggers that support NL? » Topic Opener
Heya! I’m curious, are there any uncensored taggers that support neutral language? I need one because I’m working on a pony enhancer for Anima, which is a model that supports both NL and tags
Creative Corner » Should I keep making LoRAs, or not? Or are my LoRAs complete garbage » Post 2
No, I know how to make LoRAs. It’s just that when you get spammed with all kinds of garbage in your DMs and even on your phone for 4 years straight, you burn out. Because of that, I deleted my Civitai account. I wanted to delete this one too, but I changed my mind
Creative Corner » Should I keep making LoRAs, or not? Or are my LoRAs complete garbage » Post 1
@Cypher
If you don’t mind me asking, what kind of hate were you getting? was it “this lora sucks” or “This sucks you should stop training”? just asking because if it’s the first option, I’m more than happy to send you resources for training
If you don’t mind me asking, what kind of hate were you getting? was it “this lora sucks” or “This sucks you should stop training”? just asking because if it’s the first option, I’m more than happy to send you resources for training
Creative Corner » Should I keep making LoRAs, or not? Or are my LoRAs complete garbage » Topic Opener
After 4 years, I feel like I just wasted my time. I just gave up and deleted my Civitai account because of all the hate I was getting. I won’t name anyone to avoid drama, but I’m just sick and tired of being everyone’s punching bag.
Creative Corner » Creating your own LORAs » Post 3
@Equum
Sadly, I do not know of any ways of getting two different character LoRAs to work together other than decreasing both their strengths and hoping for the best or resorting to inpainting.
Sadly, I do not know of any ways of getting two different character LoRAs to work together other than decreasing both their strengths and hoping for the best or resorting to inpainting.
Creative Corner » Creating your own LORAs » Post 2
Thanks for sharing! That seems more approachable than I thought. Do you find you need to do anything special in order to end up using many of your LORAs at the same time without them interacting weirdly?
Creative Corner » Creating your own LORAs » Post 1
I think I’m qualified to comment on this subject as I’ve made over 200 MLP character LoRAs for SDXL-based models (mostly Illustrious, though I started with PDXL 6 and have recently shifted to NoobAI).
One thing I have found is that a small, varied and well-tagged dataset is far better than a large one with just passable tagging and not that much variety. I generally use around 30 distinct images of the character (a minimum of around a dozen pics and a maximum of around 50) when training my LoRAs.
After I gather the images for the dataset, I run them all through an autotagger and then touch up its results (adding a tag for the character, removing tags that don’t apply, adding missing ones).
I think I have the capacity to train LoRAs for Flux.2, but I have no clue how to tag images for one (at the moment), so I haven’t done anything of that sort yet.
Creative Corner » Creating your own LORAs » Topic Opener
I’ve been gaining experience with PonyDiffusion and enjoying the easy knowledge it has of MLP characters, but run into some problems with fringe characters it has misconceptions of (characters are the wrong gender, have 90% correct features but random horns or other features, presented in biases acitons or poses, etc). I sometimes find pre-existing LORA’s that help with this, but sometiems the LORA’s themselves cause similar hiccups or interact with existing projects in a negative way.
I’ve recently started dabbling with FLUX2, and while it seems much more useful in creative direction and revision, it really seems to have no concepts of the pony world. Which gets me considering getting into LORA creation. There must be some potential here, seeing how impressive the PonyDiffusion project’s results are for the fandom as a whole and how little the base models seem to know.
I’m under the impression that making a LORA is simply a matter of organizing samples, and relativly trivial to run if you are willing to use a cloud serivce?
I’ve seen some others on here referencing their own LORA creation, and wondering what your experiences have been like. Is this an unrealistic thing to consider doing solo for specific characters, or do any of you find it useful? Is it relatively simple on a base model like SDXL/PXL, and unrealistic on a pony-naive model like Flux?
Creative Corner » LoRA - Characters » Post 85
Background Pony #8160
@Cypher
Well… that’s sucks. I liked these LoRAs… I can’t gen locally so it’s quite a blow for me.
Well… that’s sucks. I liked these LoRAs… I can’t gen locally so it’s quite a blow for me.
Creative Corner » LoRA - Characters » Post 84
Civit, Channel’s gone. Who cares about the 800 followers, I’m a nobody anyway
Creative Corner » LoRA - Characters » Post 83
@Cypher
On Civit? Or here on Tantabus?
On Civit? Or here on Tantabus?
Here on Tantabus, you’ll need to have an administrator do it. On Civitai, you’ll need to go to the bottom of the account settings page (account settings is the gear at the bottom of the top-right dropdown menu)
Creative Corner » LoRA - Characters » Post 82
How do I delete my account?
Showing results 1 - 25 of 382 total
Default search
If you do not specify a field to search over, the search engine will search for posts with a body that is similar to the query's word stems. For example, posts containing the words winged humanization, wings, and spread wings would all be found by a search for wing, but sewing would not be.
Allowed fields
| Field Selector | Type | Description | Example |
|---|---|---|---|
author | Literal | Matches the author of this post. Anonymous authors will never match this term. | author:Joey |
body | Full Text | Matches the body of this post. This is the default field. | body:test |
created_at | Date/Time Range | Matches the creation time of this post. | created_at:2015 |
id | Numeric Range | Matches the numeric surrogate key for this post. | id:1000000 |
my | Meta | my:posts matches posts you have posted if you are signed in. | my:posts |
subject | Full Text | Matches the title of the topic. | subject:time wasting thread |
topic_id | Literal | Matches the numeric surrogate key for the topic this post belongs to. | topic_id:7000 |
topic_position | Numeric Range | Matches the offset from the beginning of the topic of this post. Positions begin at 0. | topic_position:0 |
updated_at | Date/Time Range | Matches the creation or last edit time of this post. | updated_at.gte:2 weeks ago |
user_id | Literal | Matches posts with the specified user_id. Anonymous users will never match this term. | user_id:211190 |
forum | Literal | Matches the short name for the forum this post belongs to. | forum:meta |