qwen-image-2512-sd β€” Qwen-Image-2512 + Lightning 8-step, curated for Enclave's sdcpp backend

Component-layout volume for enclave.host image generation: the Qwen-Image-2512 transformer with the lightx2v Lightning 8-step distillation LoRA merged into the weights, quantized to Q8_0 by the same stable-diffusion.cpp revision the fleet serves with. Generates in 8 steps at cfg 1.0.

file what sha256
diffusion.gguf (20.2 GiB) Qwen-Image-2512 MMDiT + Lightning 8-step merge, Q8_0 86aafc37f65dfb4da7be8436ff6a3d91b12203ab9b855448d3d452398fb99ff2
llm.gguf (7.5 GiB) Qwen2.5-VL-7B-Instruct text encoder, Q8_0 ee770c700d7429cc6f0c74d6c7ab3c063bf521312fc36e80776d1d79bc9fa4ad
vae.safetensors (242 MiB) Qwen-Image 16-ch VAE a70580f0213e67967ee9c95f05bb400e8fb08307e017a924bf3441223e023d1f

Provenance

Every input pinned by revision; reproduction is tools/merge-lightning.sh in the image-generator app repo (streaming bf16 LoRA merge, then sd-cli -M convert --type q8_0):

Smoke-tested at that same revision: 8 steps, cfg 1.0, 512Γ—512, seed 7, euler β€” coherent output verified visually before upload.

Serving (sd.cpp)

sd-cli --diffusion-model diffusion.gguf --llm llm.gguf --vae vae.safetensors \
  -p "a red fox in snow, studio lighting" --cfg-scale 1.0 --steps 8 -W 1024 -H 1024

~34 GB peak VRAM at 1024px with tiled VAE decode. Component filenames are generic on purpose: Enclave's ENCLAVE_SD_*_FILE envs are node-global, so every SD volume on a node shares the same relative names.

Downloads last month
129
GGUF
Model size
20B params
Architecture
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for EnclaveHost/qwen-image-2512-sd

Quantized
(17)
this model