Creator claims breakthrough in character consistency using MiniMax H3 with custom LoRA and masking
linoy_tsaban · x · 2026-10-13
AI video creator akatzai reports a breakthrough on character V2: solid performance transfers achieved using MiniMax H3 ref2va with a custom character V1 LoRA plus prompt and masking techniques — no Seedance or Higgsfield involved. More tests planned, especially with Alisson's upcoming LoRA.
More from Multimodal
- toyxyz open-sources dual Anima ControlNet-LLLite adapters for 3D pose and region control — bdsqlsz · 2026-10-13
- Midjourney sref 3978901914 yields clean fine-pen silhouette illustrations — michaelrabone · 2026-10-13
- Horror-cabaret AI music video made with Claude, Grok Imagine, Midjourney and Suno — Match_Living · 2026-10-13
- Layering three Midjourney --sref codes yields cinematic film-like imagery — sergeantsref · 2026-10-13
- Metal anime MV 'Sunset' explores the anxiety of being replaced by AI — Aggravating_Copy_140 · 2026-10-13
- Akool Film Challenge entry: AI-generated 'BLUE THUNDER vs INFERNO' fight short — jijo6686 · 2026-10-13