Views
No views yet
Qwen/Qwen-Image-Edit-2511 transformer, produced
with Comfy-Org/comfy-quants
(export-model-int8-tensorwise). Loads natively in stock ComfyUI >= v0.27.0
(QUANT_ALGOS["int8_tensorwise"], SM >= 7.5 / Turing+) — no custom node required.models/diffusion_models/, load via UNETLoader); pair with
the usual Qwen-Image-Edit text encoder and VAE.time_text_embed/img_in/norm_out/
proj_out/txt_in kept bf16); all 839 ConvRot-rotated (regular Hadamard,
group 256).int8 weight + float32 [out,1] scale + comfy_quant marker
{"format": "int8_tensorwise", "convrot": true, "convrot_groupsize": 256}
(byte-exact to stock ComfyUI's save path).__index_timestep_zero__ sentinel required for correct 2511
reference-image conditioning.