My final release. Thank you to everyone who supported me, it was fun being part of this community :).

This adaptation used prompts and model-generated conditioning targets, with no image dataset.

I baked my TextFusion LoRA’s influence into TextFusion and trained Text-In to handle its outputs. Both are included in this checkpoint; no separate LoRA or adapter is needed at inference.

Responsibility and Output Disclaimer

This Checkpoint modifies the model’s text-conditioning behavior but does not determine, authorize, endorse, supervise, or control the images produced by individual users, prompts, workflows, checkpoints, samplers, or third-party software.

Generated outputs remain dependent on the base model, user-provided conditioning, inference configuration, and the surrounding generation pipeline. The author assumes no responsibility or liability for what users choose to generate, how generated material is used, or whether any output complies with applicable laws, platform rules, licensing terms, or third-party rights.

Users are solely responsible for their prompts, generated outputs, distribution decisions, and use of this Checkpoint.