This workflow allows you to harness the power of FLUX.1 [dev] within ComfyUI. Follow these steps to set up and run the model.The true "simplest" version of a Flux workflow can be found <a rel="ugc" href="https://comfyanonymous.github.io/ComfyUI_examples/flux/">here</a>, but it uses the FP8 version which is slightly worse. For that reason, I do not use the "Load Checkpoint" node version of the workflow.Note: To train LoRAs, see my video guide here: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/6533/how-to-train-a-lora-for-flux1-dev-with-simpletuner">https://civarchive.com/articles/6533/how-to-train-a-lora-for-flux1-dev-with-simpletuner</a>Instructions:<ol><li>Model Placement:<ul><li>Place the FLUX.1 [dev] checkpoint in <code>ComfyUI/models/unet</code> (not in checkpoints folder)</li></ul></li><li>Download Required Files:<ul><li>Original weights: <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/flux1-dev.sft">flux1-dev.sft</a></li><li>FP8 version (for &lt;24GB VRAM systems): <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/flux-fp8/blob/main/flux1-dev-fp8.safetensors">flux1-dev-fp8.safetensors</a></li><li>Text encoders (place in <code>ComfyUI/models/clip</code>): <a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main">flux_text_encoders</a></li><li>VAE (place <code>ae.sft</code> in <code>ComfyUI/models/vae</code>): <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/ae.sft">ae.sft</a></li><li>For lower RAM usage, download the FP8 T5XXL encoder (with some quality degradation)</li></ul></li><li>Low VRAM Setup:<ul><li>Launch ComfyUI with the "--lowvram" argument (add to your .bat file) to offload the text encoder to CPU</li></ul></li><li>Performance Notes:<ul><li>Confirmed to run on:<ul><li>RTX 3090 (24GB): 1.29s/it</li><li>RTX 4070 (12GB): 85s/it</li></ul></li><li>Both tests used the FP8 quantized version. Note that the 4070 is significantly slower.</li></ul></li><li>Preview Setup:<ul><li>Update your ComfyUI to the latest version</li><li>In the Manager menu, set "Preview Method" to "Auto"</li></ul></li></ol><h2 id="using-the-workflow-wxiqtuzaz">Using the Workflow</h2><ol><li>Load the provided workflow file into ComfyUI</li><li>Adjust your prompts and parameters as desired</li><li>Run the workflow to generate images</li></ol>Note: This workflow includes a custom node for metadata. It can run in vanilla ComfyUI, but you may need to adjust the workflow if you don't have this custom node installed.<h2 id="introduction-to-flux.1-dev-d4v8eyulb">Introduction to FLUX.1 [dev]</h2>FLUX.1 [dev] is a groundbreaking 12 billion parameter rectified flow transformer for text-to-image generation, developed by Black Forest Labs. As part of the innovative FLUX.1 suite of models, it represents a significant leap forward in image synthesis technology, offering:<ul><li>State-of-the-art image quality and prompt adherence</li><li>Competitive performance with closed-source alternatives</li><li>Enhanced efficiency through guidance distillation training</li><li>Support for diverse aspect ratios and resolutions (0.1 to 2.0 megapixels)</li></ul>Black Forest Labs, founded by distinguished AI researchers and engineers, brings a wealth of experience from developing foundational generative AI models like VQGAN, Latent Diffusion, and Stable Diffusion. FLUX.1 [dev] showcases their commitment to pushing the boundaries of AI-generated imagery.<h2 id="license-and-usage-4qnc5qkk5">License and Usage</h2>FLUX.1 [dev] is released under a non-commercial license. Please refer to the official <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md">FLUX.1 [dev] license</a> for full terms and conditions. This model is intended for research, personal projects, and non-commercial use only.Enjoy exploring the capabilities of FLUX.1 [dev] with this ComfyUI workflow!

[Simple+Advanced] FLUX.1 ComfyUI Workflows

This version bypasses applying the LoRA to the text encoder. This is recommended since current LoRAs for FLUX do not train t5.

SimpleAdvancedFLUX1_loraSupportV2NoCLIP.zip

LoRA Support v2 (No CLIP)

LoRA Support

txt2img w/ CFG + Shift

txt2img with guidance

Basic Workflow

This workflow allows you to harness the power of FLUX.1 [dev] within ComfyUI. Follow these steps to set up and run the model.The true "simplest" version of a Flux workflow can be found <a rel="ugc" href="https://comfyanonymous.github.io/ComfyUI_examples/flux/">here</a>, but it uses the FP8 version which is slightly worse. For that reason, I do not use the "Load Checkpoint" node version of the workflow.Note: To train LoRAs, see my video guide here: <a target="_blank" rel="ugc" href="https://civitai.com/articles/6533/how-to-train-a-lora-for-flux1-dev-with-simpletuner">https://civitai.com/articles/6533/how-to-train-a-lora-for-flux1-dev-with-simpletuner</a>Instructions:<ol><li>Model Placement:<ul><li>Place the FLUX.1 [dev] checkpoint in <code>ComfyUI/models/unet</code> (not in checkpoints folder)</li></ul></li><li>Download Required Files:<ul><li>Original weights: <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/flux1-dev.sft">flux1-dev.sft</a></li><li>FP8 version (for &lt;24GB VRAM systems): <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/flux-fp8/blob/main/flux1-dev-fp8.safetensors">flux1-dev-fp8.safetensors</a></li><li>Text encoders (place in <code>ComfyUI/models/clip</code>): <a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/tree/main">flux_text_encoders</a></li><li>VAE (place <code>ae.sft</code> in <code>ComfyUI/models/vae</code>): <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-schnell/blob/main/ae.sft">ae.sft</a></li><li>For lower RAM usage, download the FP8 T5XXL encoder (with some quality degradation)</li></ul></li><li>Low VRAM Setup:<ul><li>Launch ComfyUI with the "--lowvram" argument (add to your .bat file) to offload the text encoder to CPU</li></ul></li><li>Performance Notes:<ul><li>Confirmed to run on:<ul><li>RTX 3090 (24GB): 1.29s/it</li><li>RTX 4070 (12GB): 85s/it</li></ul></li><li>Both tests used the FP8 quantized version. Note that the 4070 is significantly slower.</li></ul></li><li>Preview Setup:<ul><li>Update your ComfyUI to the latest version</li><li>In the Manager menu, set "Preview Method" to "Auto"</li></ul></li></ol><h2 id="using-the-workflow-wxiqtuzaz">Using the Workflow</h2><ol><li>Load the provided workflow file into ComfyUI</li><li>Adjust your prompts and parameters as desired</li><li>Run the workflow to generate images</li></ol>Note: This workflow includes a custom node for metadata. It can run in vanilla ComfyUI, but you may need to adjust the workflow if you don't have this custom node installed.<h2 id="introduction-to-flux.1-dev-d4v8eyulb">Introduction to FLUX.1 [dev]</h2>FLUX.1 [dev] is a groundbreaking 12 billion parameter rectified flow transformer for text-to-image generation, developed by Black Forest Labs. As part of the innovative FLUX.1 suite of models, it represents a significant leap forward in image synthesis technology, offering:<ul><li>State-of-the-art image quality and prompt adherence</li><li>Competitive performance with closed-source alternatives</li><li>Enhanced efficiency through guidance distillation training</li><li>Support for diverse aspect ratios and resolutions (0.1 to 2.0 megapixels)</li></ul>Black Forest Labs, founded by distinguished AI researchers and engineers, brings a wealth of experience from developing foundational generative AI models like VQGAN, Latent Diffusion, and Stable Diffusion. FLUX.1 [dev] showcases their commitment to pushing the boundaries of AI-generated imagery.<h2 id="license-and-usage-4qnc5qkk5">License and Usage</h2>FLUX.1 [dev] is released under a non-commercial license. Please refer to the official <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md">FLUX.1 [dev] license</a> for full terms and conditions. This model is intended for research, personal projects, and non-commercial use only.Enjoy exploring the capabilities of FLUX.1 [dev] with this ComfyUI workflow!This version bypasses applying the LoRA to the text encoder. This is recommended since current LoRAs for FLUX do not train t5.

Files with SHA256: 030000a2f4ce44d51389b9c0cb091dfe52becd28739f3df08c8459359626004c