rzgar/wan2.2_i2v_fp8_e4m3fn_scaled_hq

Source: 🤗image-to-videoapache-2.046 GBother✓ 6 checksumsupdated 110d ago

Wan2.2 I2V — HQ Hybrid Scaled FP8

Left: This model | Right: BF16 | Fixed seed, Same LightX2V and prompt Your browser does not support the video tag.

Quantized from: Wan2.2-I2V-A14B-FP32-ComfyUI. High-fidelity hybrid scaled FP8.

FFN -> float8_e4m3fn + per-tensor scale_weight (MSE-tuned)
All attention -> motion / identity preserved
patch_embedding -> FP32

attention is not quantized. Better I2V fidelity.

CommentsShare your thoughts and shape the future of sovereign AI.

@rzgar is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @rzgar

Files and sources

✓SourceAvailable on 🤗

✓Checksums6 recorded

3TorrentNot listed

4SwarmNot checked

Source revision: c60c22bed121…
Witnessed: 20 Sept 2026, 20:01 UTC
Weight files: 6
Model size: 46 GB
Downloads · last month: 120
Publisher: Unclaimed

Weights

Other

Weights46 GB
2 files
wan2.2_i2v_high_noise_14B_fp8_e4m3fn_scaled_hq.safetensors 23 GBwan2.2_i2v_low_noise_14B_fp8_e4m3fn_scaled_hq.safetensors 23 GB

Family

↑ Quantized from Wan-AI/Wan2.2-I2V-A14B

View provenance entry #4809 →

Weights

Other

Weights46 GB
2 files
wan2.2_i2v_high_noise_14B_fp8_e4m3fn_scaled_hq.safetensors 23 GBwan2.2_i2v_low_noise_14B_fp8_e4m3fn_scaled_hq.safetensors 23 GB

Family

↑ Quantized from Wan-AI/Wan2.2-I2V-A14B

Seed this model

Have the files? Submit a torrent.

Submit a torrent →

>_Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo rzgar/wan2.2_i2v_fp8_e4m3fn_scaled_hq ./model-folder