FlowDIS Int8 Convrot

--- license: other license_name: picsart-flowdis-model-license license_link: LICENSE base_model: PAIR/FlowDIS tags: - image-segmentation - dichotomous-image-segmentation - quantization - int8 - flux --- # FlowDIS transformer — INT8 ConvRot INT8 quantization of the [FlowDIS](https://huggingface.co/PAIR/FlowDIS) DiT (12B, FLUX.1-schnell architecture) with group-wise Hadamard rotations ([ConvRot, arXiv:2512.03673](https://arxiv.org/abs/2512.03673)), in the ComfyUI-native quantized checkpoint format produced by [convert_to_quant](https://pypi.org/project/convert-to-quant/). Made for [Any Prompt DIS](https://github.com/Albertchen98/any-prompt-dis), whose low-VRAM mode (`--int8 --t5-int4`) runs the full segmentation pipeline in **~21 GiB peak VRAM at 1024²** (~18.4 GiB at 512²) — it fits a 24 GB card, which the bf16 pipeline (~35 GiB peak) does not. Quantizing this checkpoint yourself requires loading the bf16 transformer, so a 24 GB card also cannot produce it locally — hence this pre-quantized upload. ## Details - 228 `double_blocks`/`single_blocks` linear layers quantized to INT8 (row-wise scales, ConvRot group size 256, rotations pre-applied to weights); input/modulation/final layers kept in bf16. - End-to-end relative error vs bf16: ~1.2% on mask latents; visually indistinguishable masks in our tests. - Runtime: `flowdis/quant.py` in the repo above — uses the fused `comfy-kitchen` INT8 kernel when available (quantized linears ~1.5× faster than bf16), otherwise a `torch.compile` fallback. Reproduce from the bf16 checkpoint: ```bash pip install convert-to-quant ctq -i flowdis-transformer.safetensors \ -o flowdis-transformer-int8-convrot.safetensors \ --comfy_quant --int8 --convrot --convrot-group-size 256 \ --exclude-layers "img_in|txt_in|time_in|vector_in|mod|final_layer" \ --save-quant-metadata ``` ## Usage ```bash # place it next to the other FlowDIS weights: hf download Albertchen96/FlowDIS-int8-convrot flowdis-transformer-int8-convrot.safetensors \ --local-dir <root_model_dir> # then, in the any-prompt-dis repo: python inference_si.py --root-model-dir <root_model_dir> --int8 \ --image-path input.jpg --prompt "dog" --output-path mask.png ``` ## License Derivative of the FlowDIS weights by Picsart AI Research; distributed under the same [PicsArt Inc. FlowDIS Model License](LICENSE) (non-commercial). Review it before redistribution o...