--- license: other license_name: flux-non-commercial-license license_link: https://huggingface.co/black-forest-labs/FLUX.2-dev/blob/main/LICENSE.md base_model: alibaba-pai/FLUX.2-dev-Fun-Controlnet-Union base_model_relation: quantized tags: - flux - flux2 - controlnet - fp8 - e4m3fn - comfyui - quantization --- # FLUX.2-dev-Fun-Controlnet-Union-2602 — JLC FP8 A reproducibly generated **mixed-FP8 E4M3FN quantized derivative** of Alibaba-PAI's `FLUX.2-dev-Fun-Controlnet-Union-2602.safetensors`, produced independently by the JLC project. This release is intended for the **FLUX.2-dev Union ControlNet path in ComfyUI**. It is not a FLUX.2 Klein ControlNet. **License:** FLUX Non-Commercial License v2.1. Non-commercial use only. See [`LICENSE`](https://huggingface.co/Damkohler/FLUX.2-dev-Fun-Controlnet-Union-2602-JLC-FP8/blob/main/LICENSE) and [`NOTICE.md`](https://huggingface.co/Damkohler/FLUX.2-dev-Fun-Controlnet-Union-2602-JLC-FP8/blob/main/NOTICE.md). > This is an independent derivative release. It is **not an official product of, and has not > been endorsed, approved, or validated by, Black Forest Labs Inc. or Alibaba-PAI**. ## Checkpoint **File:** FLUX.2-dev-Fun-Controlnet-Union-2602-JLC-fp8mixed-e4m3fn.safetensors **Size:** 4,306,658,528 bytes **Precision:** 48 FP8 E4M3FN weights · 28 protected BF16 tensors · 96 FP32 scale tensors **Tensor keys:** 172 **SHA-256 fingerprint:** `b4f41f3e…b4360634ec` — [full checksum](https://huggingface.co/Damkohler/FLUX.2-dev-Fun-Controlnet-Union-2602-JLC-FP8/blob/main/checksums.txt) The published checkpoint is byte-identical to the authoritative reproducibly generated and validated release artifact. ## Examples The examples below were generated with the release checkpoint. Each uses a **single preprocessed ControlNet hint at strength 0.50**, active across the full **0.00–1.00** inference interval. Only the **hint / generated-output pair** is shown; the licensed Adobe Stock source photographs are not embedded in these example files. The selected set intentionally spans several different conditioning representations while showing two challenging articulated subjects. ### DWPose — Ballerina Pose-skeleton conditioning. ![DWPose ballerina hint and generated output](assets/examples/ballerina_dwpose.jpg) ### HED — Skater Edge / line-structure conditioning. ![HED skater hint and generated output](assets/examples/skater_hed.jpg) ### DepthAnythingV2 — Skater Depth / volume conditioning. ![DepthAnythingV2 skater hint and generated output](assets/examples/skater_depthanythingv2.jpg) ### DSINE Normal Map — Ballerina Surface-orientation / normal-map conditioning. ![DSINE normal-map ballerina hint and generated output](assets/examples/ballerina_dsine_normal.jpg) ### Color — Ballerina Low-frequency color / spatial-layout conditioning. ![Color ballerina hint and generated output](assets/examples/ballerina_color.jpg) ### ComfyUI workflow This sample ComfyUI workflow demonstrates multi-control conditioning with the JLC FP8 checkpoint. It combines DWPose, HED, and DepthAnythingV2 hints and can be used as a starting point for reproducing examples like those shown above. Both the PNG and JSON are ready for direct loading into ComfyUI; the PNG can also be drag-and-dropped onto the ComfyUI canvas. [**Download the workflow JSON**](assets/workflows/jlc_flux2_fp8_multicontrol_workflow.json) ![JLC FLUX.2 FP8 multi-control ComfyUI workflow](assets/workflows/jlc_flux2_fp8_multicontrol_workflow.png) ## What was quantized This is a **selective mixed-precision checkpoint**, not a global FP8 cast. The JLC quantization policy stores 48 large weight tensors as FP8 E4M3FN, retains 28 protected tensors in BF16, and adds 96 FP32 scale tensors used by the mixed-precision execution path. The immediate source checkpoint is: - **Publisher:** Alibaba-PAI - **Repository:** [`alibaba-pai/FLUX.2-dev-Fun-Controlnet-Union`](https://huggingface.co/alibaba-pai/FLUX.2-dev-Fun-Controlnet-Union) - **Checkpoint:** `FLUX.2-dev-Fun-Controlnet-Union-2602.safetensors` - **Source SHA-256 fingerprint:** `516532a8…b0a7a794` — [full checksum](https://huggingface.co/Damkohler/FLUX.2-dev-Fun-Controlnet-Union-2602-JLC-FP8/blob/main/checksums.txt) ## Validation The release artifact passed the following acceptance checks: - toolkit-driven quantization: **PASS** - independent reopened-file verification: **PASS** - **172 / 172 tensor payloads reproduced byte-for-byte** against the independently generated **FP8 validation reference** - native ComfyUI mixed-precision load: **PASS** - matched runtime validation at 1024 × 1536: **pixel-identical** against the validated **FP8 reference artifact** These results establish deterministic reproduction and successful execution in the validated environment. They do not claim universal numerical identity across every hardware platform, workflow, attention backend, resolution, or future software version. ## ComfyUI use This checkpoint is supported through **JLC Flux2 ControlNet v1.1.0 or later**: https://github.com/Damkohler/JLC-Flux2-ControlNet Place the checkpoint in your ComfyUI ControlNet model directory and select it with **JLC Flux2 ControlNet Loader**. The unified loader automatically supports compatible dense BF16 FLUX.2 Fun ControlNet checkpoints and the JLC mixed FP8/BF16 Union-2602 checkpoint through the same runtime node family. No separate FP8 loader, Apply node, or FP8-specific workflow path is required. The remaining JLC Flux2 ControlNet nodes—including Apply, Orchestrator, reference-image conditioning, cache preparation, and experimental in/out-paint support—operate through the same shared ControlNet runtime interface. Validated example workflows are provided with the JLC Flux2 ControlNet release. ## Reproducibility The quantization/calibration toolkit and detailed reproducibility, validation, provenance, and methodology materials used to produce this checkpoint are currently being prepared for public release. The release artifact itself has already completed the validation summarized above. The toolkit publication will provide the supporting material for reproducing and independently verifying the mixed FP8/BF16 checkpoint from the original BF16 source. Model inference does not depend on the toolkit and is supported through the public **JLC Flux2 ControlNet** package linked above. ## License and attribution The checkpoint is a derivative of a FLUX model and is **not** relicensed under MIT, Apache-2.0, GPL, or another permissive software/model license. The model derivative is distributed under the **FLUX Non-Commercial License v2.1** included in [`LICENSE`](https://huggingface.co/Damkohler/FLUX.2-dev-Fun-Controlnet-Union-2602-JLC-FP8/blob/main/LICENSE). No commercial or production rights are granted by this repository. The required Black Forest Labs attribution, source-model attribution, modification statement, and non-endorsement statement are reproduced in [`NOTICE.md`](https://huggingface.co/Damkohler/FLUX.2-dev-Fun-Controlnet-Union-2602-JLC-FP8/blob/main/NOTICE.md). The JLC software used to produce and run the model is licensed separately in its respective software repositories; those software licenses do not relicense this checkpoint. ## Author / derivative project Independent mixed-FP8 quantization and validation work: **JLC / José Luis Cordova** The repository metadata points to Black Forest Labs' current FLUX.2-dev license page; the complete license text is also included locally in this repository.