Sign up

Asirus/Minimax-H3-Latent-Upscaler-BF16-MAXQUALITY

🤗 Hugging Face sourceapache-2.02.8 GBother✓ Checksums witnessedupdated today
No torrent yet →

Minimax H3 Latent Upscaler (3D) — BF16 Conservative v5

MAXQUALITY re-quantization from FP32 source with conservative mixed-precision fallback.

📥 Download

File Size Format
minimax_h3_bf16_CONSERVATIVE_v5.safetensors ~658 MB BF16 + FP16 fallback

🎯 What changed (vs original)

Original BF16 (author) This v5
Source FP16 (naive conversion) FP32 (full precision)
Strategy .to(bfloat16) Conservative mixed-precision
Outlier correction ❌ None ❌ Not needed (clean BF16)
Mixed precision ❌ 0% FP16 ✅ 150 tensors FP16 (norm/head/tail/embed)
Conv layers Distorted Pure BF16
Artifacts Flickering, "soap" None

🚀 Usage (ComfyUI)

Place in: ComfyUI/models/latent_upscale_models/

Node settings:

  • precision: bf16
  • device: cuda
  • tile_size: 256
  • temporal_overlap: 2-4

🔬 Technical details

  • Base model: LBH-123-AI/Minimax_h3_latent_Upscaler
  • Source dtype: FP32 (minimax_h3_latent_upscaler_3d_fp32.pth)
  • Target dtype: BF16 + FP16 fallback
  • Total tensors: 322
  • FP16 fallback: 150 tensors (GroupNorm, conv_in, conv_out, embed, emb_layers)
  • BF16 pure: 172 tensors (all conv weights without modifications)
  • Re-quantization: Conservative (no outlier correction, no smoothing, no calibration)

⚠️ License

This is a derivative work of Minimax H3 Latent Upscaler by LBH-123-AI.

License: Apache-2.0

You must comply with the original license terms. No additional restrictions applied.

🙏 Credits

  • Original model: LBH-123-AI
  • Based on: LTX 2.5 bf16 native approach