Views
No views yet
int8_tensorwise + ConvRot) conversions of two MiniMax-H3 fl2va finetunes,
in ComfyUI's baked-adaLN checkpoint format. Both files are 19.53 GB, so they fit
a 24 GB card as the diffusion model.ComfyUI/models/diffusion_models/ and load with Load Diffusion Model
(UNETLoader), weight_dtype: default. You still need the matching H3 text encoder
and the video/audio VAEs.| File | Size | Source |
|---|---|---|
10Eros_Max_h3_fl2va_pruned_int8_convrot.safetensors | 19.53 GB | TenStrip/10Eros-Max (bf16) |
PinkCherry_h3_fl2va_pruned_int8_convrot.safetensors | 19.53 GB | SexGod1979/PinkCherry_MiniMax-H3 (int8, dense adaLN) |
blocks.0-49 × attn.qkv_proj, attn.out_proj, mlp.fc1, mlp.fc2)
stored as int8 with per-output-channel fp32 scales and a per-layer descriptor:
{"format": "int8_tensorwise", "convrot": true, "convrot_groupsize": 256}adaln_t_table [1025, 8] fp32 + adaln_proj.linear.weight [96768, 8] fp16token_refiner and final_layer left at source precisioncomfy_kitchen casts the fp32 scale down to the input dtype
before dividing, so a bf16 input quantizes through an 8-bit-mantissa divisor. That
costs ~8% accuracy and pushes extremes to -128; from fp32 the range is a clean
[-127, 127]. Measured weight error vs the bf16 source: 0.90–1.02% relative L2,
cosine ≥ 0.99994 — at the theoretical floor for per-channel INT8 with Hadamard rotation.[96768, 2688], about 12.1 GiB that ComfyUI's format
doesn't carry. Since adaLN depends only on the scalar timestep, silu(time_embedder(t))
traces a 1-D curve in R^2688 that is rank-8 to ~9e-5. Baking it:S[g] = silu(time_embedder(g/1024)), g = 0..1024
S = U diag(s) V^T -> adaln_t_table = U[:, :8] * s[:8], W' = W @ V[:, :8]time_embedder.* is then dropped. ComfyUI applies no SiLU in curve mode
(apply_silu = not use_adaln_curves), so it is folded into the table. End-to-end adaLN
error is 2.1e-4, identical on-grid and off-grid — the runtime's linear interpolation
between table rows costs nothing at this grid density, and the error sits ~50× below the
INT8 error already present in the weights.comfy.sd.load_diffusion_model load plus a forward pass through the INT8
kernel. These are structural and numerical checks — they are not a substitute for
judging output quality yourself.