Downloads · 30 days
0
q3_nocfg_25f_384x256
reneeice/q3_nocfg_25f_384x256
q3_nocfg_25f_384x256 is a machine learning model from reneeice. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
V8 Diffusion-DRF LoRA probe on Wan 2.2 I2V 14B (transformer2).
Access
Public
Updated Aug 6, 2026
Repo size
307 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors920 MB · 100%
At a glance
- Access
- Public
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026
- SHA
- 4ed34cce
Model card
From the Hugging Face model README
Q3_nocfg_25f_384x256
V8 Diffusion-DRF LoRA probe on Wan 2.2 I2V 14B (transformer_2).
- Geometry: 25f @ 384x256, K=2, no-CFG-in-grad-window
- rank16 lr5e-6 5 steps; train-geom held-out 0.8484 -> best 0.8484
- Targets: to_q, to_k, to_v, to_out.0, ffn.net.0.proj, ffn.net.2
- Base model: subnet king (hippius-hub snapshot)
Train-geometry held-out LPIPS improvements were NOT reproducible at full 832x480x81 eval geometry (all 4 probes within +-0.0008 of king baseline 0.4310).
- Created
- Aug 6, 2026
- Updated
- Aug 6, 2026