Views
No views yet
| File | Size | Source |
|---|---|---|
flux1-krea-dev-int8convrot.safetensors | 13.2 GiB (14.1 GB) | flux1-krea-dev.safetensors (22.2 GiB / 23.8 GB) |
.comfy_quant metadata for INT8 row-wise + ConvRot
weights) as a diffusion model checkpoint.convert-to-quant (ctq) CLI tool using INT8 row-wise quantization with
ConvRot (group-wise Hadamard rotation, group size 256) and Comfy-quant format. The --flux2
exclusion filter was reused here since its layer-name patterns (guidance_in, time_in, img_in,
txt_in, final_layer) happen to match FLUX.1's naming too, keeping those layers high-precision.
--exclude-layers was added on top to also keep the per-block modulation linears
(img_mod/txt_mod in the double blocks) high-precision, since FLUX.2's stream_modulation
key pattern doesn't match FLUX.1's img_mod.lin/txt_mod.lin naming.hf download black-forest-labs/FLUX.1-Krea-dev flux1-krea-dev.safetensorsuv run --with convert-to-quant --with triton --with safetensors --with tqdm --with numpy ctq \
-i flux1-krea-dev.safetensors \
-o flux1-krea-dev-int8convrot.safetensors \
--int8 --scaling_mode row --convrot --flux2 --exclude-layers 'img_mod|txt_mod' \
--comfy_quant --save-quant-metadata --simple --low-memoryflux1-krea-dev-int8convrot.safetensors: 1316 tensors, 268 layers quantized to INT8 row-wise +
ConvRot (verified via the _quantization_metadata header) across all 19 double blocks and 38
single blocks. High-precision (unquantized) layers: img_mod/txt_mod (double blocks),
guidance_in, time_in, img_in, txt_in, final_layer.--int8 — INT8 quantization instead of FP8--scaling_mode row — per-row scale factors (required for ConvRot)--convrot — group-wise Hadamard rotation (group size 256, default) to reduce INT8 quantization error--flux2 — exclusion filter; its key patterns (guidance_in, time_in, img_in, txt_in,
final_layer) happen to match this FLUX.1-based checkpoint's layer names--exclude-layers 'img_mod|txt_mod' — additionally keep per-block modulation linears high-precision--comfy_quant — Comfy quantization tensor/metadata format--simple — skip SVD optimization, use simple quantization--save-quant-metadata — embed _quantization_metadata in the safetensors header--low-memory — stream tensors during quantization to reduce RAM usage