Download README.md from NidAll/MOSS-Image-SFT-4step-Merged: direct link, hf CLI and curl.
- Browser
- Download file 2.65 kB
-
https://huggingface.co/NidAll/MOSS-Image-SFT-4step-Merged/resolve/main/README.md
- Command line
-
hf download hf://NidAll/MOSS-Image-SFT-4step-Merged/README.md
-
curl -L -o README.md https://huggingface.co/NidAll/MOSS-Image-SFT-4step-Merged/resolve/main/README.md
license: apache-2.0
base_model:
- OpenMOSS-Team/MOSS-Image-SFT
- lvladikov/MOSS-SFT-Distill-4step-LoRA
base_model_relation: merge
pipeline_tag: text-to-image
tags:
- comfyui
- moss-image
- step-distillation
- int8
- convrot
- 4-step
MOSS-Image SFT 4-step (LoRA merged): BF16 and INT8 ConvRot
lvladikov/MOSS-SFT-Distill-4step-LoRA merged into MOSS-Image SFT. No LoRA node needed. Not an official OpenMOSS or Comfy-Org product.
| File | Format | Size |
|---|---|---|
moss_image_sft_4step_merged_bf16.safetensors |
BF16 | 10.16 GB |
moss_image_sft_4step_merged_int8_convrot.safetensors |
int8_tensorwise + ConvRot, per-row (layout identical to Comfy-Org moss_image_sft_int8_convrot.safetensors) |
5.41 GB |
Put a file in ComfyUI/models/diffusion_models/ and load it with Load Diffusion Model. Workflows: workflows/.
Settings (keep them)
4 steps · euler · CFG 1 (BasicGuider) · ManualSigmas 1.0, 0.91, 0.717, 0.024, 0.0 · trained sizes 768x512 to 1824x1024 (and portrait), multiples of 16.
INT8 needs an NVIDIA GPU with INT8 tensor cores (SM 7.5+) and a ComfyUI with native int8_tensorwise + ConvRot support.
How it was made
moss_sft_4step_rank_64_lora_comfyui.safetensors(rev 2ec5241400bf) merged intomoss_image_sft_bf16.safetensors(Comfy-Org/MOSS-Image rev 2929efe3cdd5) in fp32 at strength 1.0, ComfyUI's runtime ruleW + (alpha / rank) * up @ down. BF16 rounds once, from fp32.- INT8 from the fp32 merge: group-wise regular Hadamard rotation (ConvRot, group [256]),
per-row symmetric INT8 (
mseclip). Layer selection and metadata mirror Comfy-Org's official SFT INT8 file.
Checks that passed
- BF16: header identical to the base; 211 tensors byte-identical; 168 merged tensors equal bf16(W + ΔW) exactly (median ‖ΔW‖/‖W‖ = 0.0014).
- INT8: header and every
comfy_quantidentical to the official file; all 168 quantized layers reconstruct the merged fp32 weight, median relative error 0.0084 (max 0.0096); the official file's own error on the unmerged base: 0.0086. - Quantizer basis proven on the unmerged base against the official file (median exact-match 1.0000); bit-identical to comfy-kitchen 0.2.41.
- Remote sha256 of both checkpoints equals the local files.
Known limitations are those of the LoRA (see its card).
Credits and license
MOSS-Image by OpenMOSS-Team (Apache-2.0), ComfyUI repack by Comfy-Org. 4-step LoRA by lvladikov (Apache-2.0), NOTICE included. ConvRot math ported from comfy-kitchen (Apache-2.0). Merge and quantization by NidAll.