A four-step, native Blackwell W4A4 release of Mage-Flow Edit Turbo.
Original model · ComfyUI source weights · FP8 text encoder source · XPO3 text-to-image sibling
--- ## Download | File | Purpose | Size | |:--|:--|--:| | [`Mage-Flow-Edit-Turbo-XPO3-NVFP4.safetensors`](https://huggingface.co/ajh-code/Mage-Flow-Edit-Turbo-XPO3-NVFP4/resolve/main/Mage-Flow-Edit-Turbo-XPO3-NVFP4.safetensors?download=true) | Self-contained Edit-Turbo transformer | 4.65 GB | | [`qwen3vl_4b_fp8_scaled.safetensors`](https://huggingface.co/ajh-code/Mage-Flow-Edit-Turbo-XPO3-NVFP4/resolve/main/qwen3vl_4b_fp8_scaled.safetensors?download=true) | Shared scaled-FP8 text encoder | 5.24 GB | | [`Mage-Flow-VAE.safetensors`](https://huggingface.co/ajh-code/Mage-Flow-Edit-Turbo-XPO3-NVFP4/resolve/main/Mage-Flow-VAE.safetensors?download=true) | Shared Mage VAE | 345 MB | The transformer contains all retained BF16 tensors, 48 packed NVFP4 MLP projections, and 24 offline-fused NVFP4 QKV groups. It does not require the 8.23 GB BF16 transformer. --- ## Quick start Linux, Python 3.11, CUDA 13, and an NVIDIA Blackwell SM120 GPU are required. ```bash hf download ajh-code/Mage-Flow-Edit-Turbo-XPO3-NVFP4 --local-dir mage-edit-xpo3 cd mage-edit-xpo3 python3.11 -m venv .venv . .venv/bin/activate pip install -r requirements.txt python edit.py reference.jpg \ "Replace the background with a snowy pine forest. Keep the subject unchanged." \ --output edited.png --seed 1 --max-size 1024 ``` The included CLI uses the promoted profile automatically: four steps, CFG 1, shift 6, image-only fused GELU, calibrated FP4 bridge on all 12 blocks, and direct-HND accelerated attention on steps 1–3 with exact step-0 fallback. Every optimization has a CLI disable switch. > The public ComfyUI-XPO3 v0.3.0 nodes target text-to-image Turbo. Use the > included Edit CLI until Edit-Turbo node support is released; do not load > this checkpoint with the old Turbo Generate node. --- ## Examples | Reference | XPO3 edit | |:--:|:--:| | [](examples/dog-reference.jpg) | [](examples/dog-edited.png) | | [](examples/fruit-reference.jpg) | [](examples/fruit-edited.png) | The first edit changes the background while preserving the dog. The second changes only the tablecloth while preserving the fruit and composition. --- ## Measured on RTX 5060 Ti | 512-long-edge edit | BF16 denoise | XPO3 denoise | Speedup | |:--|--:|--:|--:| | Dog background | 0.5820 s | 0.3216 s | 1.81× | | Fruit tablecloth | 0.6285 s | 0.3469 s | 1.81× | Peak allocated memory was 5.41–5.54 GiB, 31–33% below the matched BF16 runs. These are hot denoise measurements on one local system, not universal end-to-end claims. Load, multimodal conditioning, reference encoding, denoise, and VAE decode were measured separately. ## Validated scope - Same-seed outputs were deterministic across fresh and hot repeats. - Dog identity, pose, coat, collar, and framing survived a background change. - Fruit type, count, layout, bowl, and lighting survived a tablecloth-only change. - Step 0 accelerated attention was rejected after a black-image failure and remains on exact fallback. - The release file passed checksum, tensor-coverage, zero-source-read clean loading, restoration, and two-case edit-quality gates. This is an XPO3 runtime package, not a generic portable quantization format. The bundled native libraries target Linux x86-64, Python 3.11, PyTorch 2.13.0+cu130, and SM120. MIT for the XPO3 package and Mage-derived runtime. The scaled-FP8 Qwen3-VL component and bundled SpargeAttn code are Apache-2.0; see [`THIRD_PARTY_NOTICES.md`](THIRD_PARTY_NOTICES.md).