Views
No views yet
wan-core / Bernini-R runtime. The i2v sibling of
AnimeGen-T2V-A14B-Lightning-int4.| File | What |
|---|---|
high_noise_model.safetensors | fine-tuned high-noise expert, int4 (in_dim=36 = 16 noise + 4 mask + 16 image latent) |
low_noise_model.safetensors | fine-tuned low-noise expert, int4 |
vae.safetensors | 16-channel Wan VAE |
t5_encoder.safetensors | umT5-XXL text encoder |
config.json | Wan2.2-I2V-A14B config (model_type: i2v, in_dim: 36) + quantization metadata |
[noisy_latent(16), mask(4), image_latent(16)] = 36 channels. Encode a video whose first frame is
the conditioning image and the rest zeros through the 16-ch WanVAE → z_video(16); build a first-frame temporal
mask(4); y = [mask, z_video](20) is constant across steps and concatenated onto the 16-ch noisy latent each
denoise step. No separate image encoder (image_dim is null).16·seconds + 1 (must be 4n+1), 16 fps"Japanese anime style, "aidealab/AnimeGen-I2V (original-Wan keys → sanitize; key set == the A14B 1095-key
contract). The lightx2v Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1
LoRA merged offline per-expert (set_adapters([high,low],[1.0,1.0]), kohya). Attention + FFN linears quantized int4/g64.aidealab/AnimeGen-I2V (AIdeaLab / GENIAC) + the lightx2v Lightning LoRA. Unofficial
community MLX conversion; not affiliated with AIdeaLab.