Clothturn Helper

*Every like, comment, and post will support me to go further!!

Can find project files(.blend) on my Patreon Chamber | creating Game, Art | Patreon. Subscriptions can help me update further and create more~

Plan, future, coming soon...

- [ ] more data from 3d models rendering test(about 100(will post if any improvement
- [ ] more steps test (around 5000 (will post if any improvement

- [ ] better tags and prompt test (including wildcards(will post if any improvement
- [ ] charturn (also others‘ turntable) ti for sdxl/sd1.5
- [ ] charturn (also others‘ turntable)remix ver for both sd1.5 and sdxl,
based on about 60 picked-generated images to try to make the output prettier(will post if any improvement,
relate to the current version based on 20-50 3d model render images aimed at multi-view correction
- [ ] charturn age/body shape/height/suit outline/face control test(will post if any improvement
- [ ] my LoRA/models will post in public, and my train/generate tool/workflow will post on my Patreon only

Once I get 500 buzzes, I will try to train XL LoRA on CIVITAI,(3/21/2024)

Working On Training LoRA XL Now, Thank for All Your Guys~(3/22/2024)

to improve the hand/palm/finger, hair/helmet/mask, and clothing,
for controllable elements/styles, quantity, and consistency, I think it may help but not sure (have to test~)

My local GPU (RTX 4080 Laptop 12Gb VRAM) seems not enough to train XL LoRA...

!!! If you want similar results,
Please repeat most of the generate/sample settings from the raw pictures examples here,
including ControlNet(OpenPose mostly) and also others' LoRA/TI, like CharTurner | CharTurner(TI) | Baldifier slider | noline - v1.0...
different extra LoRA/TI have their special efforts, add or delete them to test what suits your targets~

Here is one of the LoRAs I trained for my new workflow, AI-powered designs, and textures(camera-based projection) tools.
for SD XL

Clothturn Helper XL - v1.0 | Stable Diffusion LoRA | Civitai

Charturn Helper Merged XL - v1.0 | Stable Diffusion LoRA | Civitai

for SD 1.5:

-Charturn Helper Merged - v4.0 | Stable Diffusion LoRA | Civitai
- Bodyturn Helper - v3.0 | Stable Diffusion LoRA | Civitai
- Faceturn Helper - v2.0 | Stable Diffusion LoRA | Civitai
- Hairturn Helper - v1.0 | Stable Diffusion LoRA | Civitai
- Clothturn Helper - v1.0 | Stable Diffusion LoRA | Civitai
- Mechturn / Armorturn Helper - v1.0 | Stable Diffusion LoRA | Civitai
Sword Gen - v1.0B | Stable Diffusion LoRA | Civitai

They work best with my character Library in the future,
including 3d models' mesh shape edit guide, auto texturing/shading, weight painting, and so on...~
Mostly design for asset creation to develop my own game,
which may help other independent developers like me.

Personally Recommend Checkpoint (Their versions are important too, personally use merged versions for different styles):
anime: Anything V5PrtRE Anything | animelike25DV11Pruned | AnyLoRA | Counterfeit-V3.0 | MechaDream | Mistoon_Sapphire - v2.0
realistic: Henmix_Real - v5c | AbsoluteReality - v1.8.1 | BeautifulRealistic - v1.0 | ChilloutMix - Chilloutmix-Ni-pruned-fp32-fix

Also training data here, about 30 percent of them rendered from artwork I created and posted before 3D models by ChamberSu1996 - Sketchfab,
the rest are bought and collected from the internet: TrainDataPack.zip
Every LoRA was trained from a relatively tiny collection including 20~ 50 pictures for this early and test version, but it still helps a lot now.

And training setting for kohya_ss for every LoRA I create, only uses different data, image size, and epoch, the rest are the same: ToonHairTurn_v1.json
(recommend trying your own better data and setting, for I am not familiar with training now, just try to make every step/feature workable this time and keep settings as simple/default as possible,
will learn further about reasonable data, tags, and train settings later,
then train better by only using my own artwork render images to ensure it will be open to use, and follow my styles/tastes)

Here are the raw picture samples with the whole generated info that can be read
(! take care of the body turn sample, they are naked bodies and not suitable to read in public~): RawPictureSample.zip

Add dynamic prompt and wildcard from Civital to help get unlimited different results,  using Gemini and Chat GPT to generate prompt wildcards for testing work well too~

if any questions or anything here interests you, Feel free to contact me by leaving a comment or mailing to [email protected]

Also Discord Channel here~
https://discord.gg/SFJFcctfgD

Every like, comment, post, and Patreon Chamber | creating Game, Art | Patreon Subscriptions can help to get the budget to update further, create more, and post them~