flux2DevFp8Scaled_fp8Scaled.safetensors

<h2 id="credits:"><strong>Credits:</strong></h2><p><strong>This model was trained and Finetuned by silveroxides</strong></p><p><strong>You can find all their models and work on Hugging Face here: </strong><a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/models"><strong>https://huggingface.co/silveroxides/models</strong></a></p><p><strong>30GB Version of </strong><a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs">black-forest-labs</a>/<a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.2-dev"><strong>FLUX.2-dev </strong>64.4GB</a></p><h2 id="you-can-find-workflow-with-samples-in-the-workflow_assets-folder."><strong>You can find workflow with samples in the </strong><a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/tree/main/workflow_assets"><strong><u>workflow_assets</u></strong></a><strong> folder.</strong></h2><p><a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/tree/main/workflow_assets">https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/tree/main/workflow_assets</a></p><h3 id="the-workflow-contains-the-information-and-links-needed-to-get-started-with-using-this-model."><strong>The </strong><a target="_blank" rel="ugc" href="https://huggingface.co/silveroxides/FLUX.2-dev-fp8_scaled/blob/main/workflow_assets/fp8_scaled_flux2_w_enhanced_prompting-workflow.json"><strong><u>workflow</u></strong></a><strong> contains the information and links needed to get started with using this model.</strong></h3><h3 id="this-fp8_scaled-model-is-faster-than-the-official-one-released-by-comfyorg-when-used-with-the-loader-in-the-workflow."><strong>This fp8_scaled model is faster than the official one released by ComfyOrg when used with the Loader in the workflow.</strong></h3><h3 id="the-custom-node-that-loads-the-model-in-the-workflow-is-necessary-to-obtain-fastest-inference-on-lower-vram-gpu."><strong>The custom node that loads the model in the workflow is necessary to obtain fastest inference on lower VRAM GPU.</strong></h3><p></p>

FLUX.2-dev-fp8_scaled: fp8-scaled: flux2DevFp8Scaled_fp8Scaled.safetensors

Credits:

You can find workflow with samples in the workflow_assets folder.

The workflow 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.