This LoRA is designed for my whole workflow mostly,
take a look at my Patreon Chamber | creating Game, Art | Patreon,
download the generation images above, then drag them to ComfyUI to load the workflow behind them, the images generated by ComfyUI will attach their worlflows~
you can also try to use it in another way,
If you are interested in or want to download
more my personal LoRAs merged checkpoints for game design
the raw generated image with generation info,
LoRA training preset files,
raw pictures data training set and tag preparation,
prompt structures
and how to model these images to 3d models,
take a look at my Patreon Chamber | 3d Asset, Dev Tool, Game | Patreon,
Subscriptions can help me update further and create more~
there are detailed posts and assets and I am willing to help if needed~
Description
FAQ
Comments (9)
You don't have triggers listed or prompts visible. No idea how to use this.
download the images and drag them to ComfyUI to load the workflow behind them
Tried using it without ComfyUI, it works with "animemodturn, front view, side view, back view, same character, character sheet" in prompt. "animemodturn" is the trigger word as far as I know
makes sense, I'm trying to do it without their workflow because it's pure madness, it's too messy to understand what's happening.
@Daru_22 please undersatnd the workflow step by step(group by group), T2I with ctrlNet first, then HiResFix(Image2Image to upsacle), then Tile upscale, finally ADetailer(face detect then fixing)
@NekoYaSan personally didn't use the 'animemodturn' to generate, but for trainning to delete unnessary details from the data set (pack all the details unable to detect and descrite by Joytag, then generated without using the word to avoid these details, to get clean and more common results) I hope it work fine~
Thank you very much, your guidance has been very helpful to me
WAI-NSFW caused color fraying, but it might have worked with the Holy Mix [illustriousXL] High contrast anime checkpoint. This might work better with noob XL checkpoints when generating online. Still in testing though.
Works shockingly well compared to the old models trying to do the same thing back with SD1.5. An amazing tool for testing character LoRAs
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.