This trained LoRA enhances capabilities in text layout and poster design, while also addressing issues such as distorted limbs and other anomalous visual artifacts. Trigger word: font. Recommended LoRA strength for general text-to-image generation: 0.3–0.4. Recommended LoRA strength for text-based poster generation: approximately 0.6. The default CFG scale is 1; if text appears broken or malformed, you may increase it to 3. For poster layouts, a CFG scale of 3 is recommended.

Video tutorial: https://youtu.be/001zm-FyjyI

Run online: https://www.runninghub.ai/post/2111467394572046338?inviteCode=rh-v1331

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support