ShoheiAI/steelwireXL

Steelwire (Torax) Style

Prompt

score_9, score_8_up, score_7_up, score_6_up, source_anime, outdoors, ocean, innertube, lens flare, 1boy, solo, topless, open mouth, smile, toned, swim trunks <lora:steelwire_AMXL_v1c-ShoAI:1>

Negative Prompt

source_pony, (hands:1.1)

Model description

This DORA is designed to recreate the style of the artist Steelwire (aka Torax). No trigger words needed, but read the description of the score tags for details. HiRes Fix is recommended for the best results. Most sample images were generated with 1.5x Latent (Nearest) upscale with ~20 steps and 0.57-0.62 denoise.

Now that there is support for DORAs on most generation platforms, I've decided that the quality increase is worth it. All future releases will be in DORA format and I will probably update my previous releases to this format, as well.

Please support the original artist wherever possible so they can continue to produce their art. Without them, LORAs such as these would not be possible.

This model is also on CivitAI and TensorArt.

USAGE NOTES:

This LORA was trained on AutismMix and is recommended to use it at full 1.0 strength. If you are using a different checkpoint, you may need to use a higher strength to maintain the style. Most images were tagged with "source_anime" and scores 6-9. This LORA should also be capable of recreating this artist's furry style by using the "furry male" tag. I'm not very experienced with tagging for furry content, so the results may not be the best.

NOTE: This LORA is NSFW capable due to being trained on Pony. If you do not want NSFW, make sure you actively prompt away from it. Many source images were censored, so you may need to put "bar censor" or "mosaic censoring" in the negative. For this pass, images were not tagged with rating_safe, rating_explicit, etc.

TAGGING NOTES:

Images were ranked in scores 6-9 as well as given the "source_anime" tag.

Score 9-7 images were the most recent and detailed, while score 7 were older images or lower detail. Score 6 images are the least detailed and also include some images sourced from manga scans that have been tagged with "source_manga" and "monochrome, screentones" tags.

Download model

Weights for this model are available in Safetensors format.

Download them in the Files & versions tab.