| --- |
| language: |
| - en |
| base_model: |
| - black-forest-labs/FLUX.2-dev |
| license: other |
| license_name: flux-dev-non-commercial-license |
| license_link: LICENSE.md |
| extra_gated_prompt: >- |
| By clicking "Agree", you agree to the [FLUX [dev] Non-Commercial License |
| Agreement](https://huggingface.co/black-forest-labs/FLUX.2-dev/blob/main/LICENSE.txt) |
| and acknowledge the [Acceptable Use |
| Policy](https://bfl.ai/legal/usage-policy). |
| tags: |
| - image-generation |
| - image-editing |
| - flux |
| - diffusion-single-file |
| - comfyui |
| - fp8_scaled |
| pipeline_tag: image-to-image |
| --- |
| |
|
|
| ## You can find workflow with samples in the [workflow_assets](https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/tree/main/workflow_assets) folder. |
|
|
| ### The [workflow](https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/blob/main/workflow_assets/fp8_scaled_flux2_w_enhanced_prompting-workflow.json) contains the information and links needed to get started with using this model. |
| ### This fp8_scaled model is faster than the official one released by ComfyOrg when used with the Loader in the workflow. |
| ### The custom node that loads the model in the workflow is necessary to obtain fastest inference on lower VRAM GPU. |
| |
| ### If you want to use mxfp8, then you need to use [silveroxides/ComfyUI-QuantOps](https://github.com/silveroxides/ComfyUI-QuantOps) custom node and custom custom comfy-kitchen [Repo with instructions](https://huggingface.co/silveroxides/Chroma1-HD-fp8-scaled/tree/main/experimental) until official support is merged. |
| ### Use [BobJohnson24/ComfyUI-Flux2-INT8](https://github.com/BobJohnson24/ComfyUI-Flux2-INT8) for int8 tensorwise model. |
| |
|  |
| |
|  |
