V1.1 - Now with better arms!

Follow the same prompting instructions as V1.0.

• Strength of 1.0-1.2 works best. For distilled model, 4 steps works great, 6 steps works even better.

• Minor update to hair tying for better results - use "Her ankles are tied to her bound [hair-bun/ponytail] by a central rope pulled taut"

• Cleave gag fixed too.

• It might give you logos in the image. Simply use "Do not include any logos in the image output" at the end of the prompt.

Flux still likes breaking anatomy, but this version is a lot more consistent with arm anatomy.

V1.0

Happy to present one of the tougher LoRA's to train! Works great with distilled model and base model. All images shown in examples are with the distilled model for reference.

Works great with 1.0 strength, adjust up or down as needed. Supports landscape and portrait both, some resolutions (like square) may break anatomy but works great 95%+ of the time.

Trained on a structured prompt like below which yields most consistent results. Framework below:

• Trigger word: "h0gti3d"

• Trigger prompt: "Woman is lying on a [surface] bound in a hogtied pose with her arms pulled behind her back and her legs bent upwards."

• Rope positioning: "She is bound with [color] rope, with the ropes tying her [wrists/elbows/arms/ankles/thighs/knees/chest/shoulders]. Her ankles are tied to her bound [wrists/hair]."

  • The bound hair part may take a few tries/seeds but on average does the job.

• Gag Options:

  • Don't include anything if you don't want a gag

  • Ball gag: "She has [color] ball gag in mouth fastened with [color] [material] straps.

  • OTM Cloth Gag/Wraparound Tape Gag: "She is gagged over-the-mouth with [color] [tape/cloth] wrapped around her mouth fastened behind her head."

  • Cleave Gag: "She has a thin strip of [color] cloth cleave gag between her lips fastened behind her head." (Note: this might be iffy sometimes it gets confused with the OTM gag but again usually it works)

• Describe the woman in natural language

• Describe the scene in natural language

• Describe the camera angle - trained on side angle, three quarter angle, front view, slightly top down views etc.

Putting it all together - SEE EXAMPLE IMAGES POSTED