V17 Update - Relight + Animation Enhancer (click show more / scroll down)<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/gh103CdD6ZU" start="0"></iframe></div>V15 Update - Ip Adapter Support !<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/ooRLYcbjkos" start="0"></iframe></div>V14 Update - Training Tools, helps to find the best intermediate models.<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/RFGMkqoqeGM" start="0"></iframe></div>V12 Update - Flux Live Portrait, Mimic Motion &amp; Flux Video Detailer<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/c2n-qgSI2Y8" start="0"></iframe></div> V11 Update - Flux Control Net (Depth, Canny, HED) plus Controlnet Inpainting with Lora.<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/TcQAzXjkR-c" start="0"></iframe></div>V10 Update - Flux Inpainting with SAM2<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/dO2o0YbBvmI" start="0"></iframe></div> V9 Update - Scene Creator - (click show more / scroll down)<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/77GfUxXV2VE" start="0"></iframe></div>V8 Update - *two videos* - (click show more / scroll down)<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/NulDE1_CnEU" start="0"></iframe></div><div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/A_t6H-pFt3k" start="0"></iframe></div> V7 Update - (click show more / scroll down)<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/FUOqtOvvf2s" start="0"></iframe></div> V6 Update -<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/L6_yi539V-s" start="0"></iframe></div> V5 Update -<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/kVmJv3dmH3k" start="0"></iframe></div> V4 Update - (click show more / scroll down)<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/uL2klICPegc" start="0"></iframe></div>V3 Update -<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/73STu8lOZCw" start="0"></iframe></div> V2 Update -<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/C7EAH8BlbpE" start="0"></iframe></div>V1 Update - (installation &amp; basic version)<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/WSuja3a5VXg" start="0"></iframe></div><h1 id="foda-flux.1-pack-for-comfyui-gxfbak2j8">Foda FLUX.1 Pack for ComfyUI</h1>article (pack v3): <a target="_blank" rel="ugc" href="https://civarchive.com/articles/6499">New Emergent Abilities of FLUX.1 Schnell [ image 2 image ]</a>v1Basic<ul><li>txt2img / img2img mode switch</li><li>8K native tiled upscaler</li></ul>v2Flux Shift<ul><li>allows model shift to be controlled</li></ul>Flux Sampler Garden<ul><li>all samplers preset for img2img, denoise variable</li></ul>v3Flux Shift Line<ul><li>No Easy use version of v2 Flux Shift (lines only)</li></ul>Flux Auto Shift<ul><li>Magic prompt + one button prompt nodes to enhance prompts automatically</li></ul>Flux Auto Shift Line<ul><li>No Easy use version of v3 Flux Auto Shift (lines only)</li></ul>v4<ul><li>updated to all previous workflows, using low sigma shift and aspect sized dimensions.</li><li>added new modules for Color correction &amp; RemBG</li><li>SDXL image Bridge, allows use of SDXL checkpoints,lora,cnets</li><li>.cube LUTs free downloads added to the bottom of this page</li></ul>v5Flux Bridge Kolors<ul><li>Kolors txt2img/img2img with CNET/IPA</li><li>txt2img/img2img with Flux1</li><li>BOOSTED Flux Upscaling ! (new feature)</li><li>all previous modules included</li></ul>V6Flux Kolors Bridge ZENKAI<ul><li>my own custom prompt styling system for flux bridge</li></ul>Pure Flux ZENKAI<ul><li>only Flux txt2img/img2img using my Zenkai prompt system</li></ul>Flux Boosted Upscaling<ul><li>image loader input, dedicated upscaling</li><li>fastest 2X upscaler on Flux</li><li>can run at 0.01 denoise with good results</li><li>BOOST YOUR SHIFT !</li></ul>V7Foda Flux Thumbnails<ul><li>Has one job only. Make Thumbnails with AI Text.</li><li>three separate controllable stages, text, background, subject</li><li>many masking options for composition</li><li>create thumbnails or posters</li><li>full control over each layer</li><li>fast and clean</li></ul>V8Foda Boosted Upscaler<ul><li>QoL improvements to the v6 release</li></ul>Floda-Flux-Lora<ul><li>Lora Stack Loader for Flux Workflow</li></ul>Foda Webcam<ul><li>fun experiment with webcam into Flux</li></ul>V9<ul><li>All 8 Main Workflows refactored with a full set of latest versions, using starndard connecting lines only.</li><li>due to popular demand with EasyUse not working for everyone :) Big Love</li></ul>Foda Scene Creator<ul><li>generate layers with Flux, using prompts in txt2img/img2img</li><li>generate the Scene, background character/objects &amp; foreground character/objects</li><li>generate Text Layers all with toggles</li><li>use fixed seeds on each layer to lock in your progress</li><li>FAST MODE: toggle dumb/Flux Upscaler for each layer, speeding it up</li></ul>V10Flux Inpainting<ul><li>used Flux with difference diffusion</li><li>manual masking in the image loading node</li></ul>Flux Inpainting SAM2<ul><li>used Florence2 LLM for prompt 2 mask</li><li>used SAM2 for segmentation into FLUX</li><li>same as above workflow for inpainting side</li></ul>V11Flux Inpainting SAM2 CNET<ul><li>Flux Inpainting SAM2 from V10 with Lora &amp; CNET Depth</li></ul>Flux Inpainting SAM2 with Depth+Canny+HED<ul><li>Flux Inpainting SAM2 from V10 with Lora &amp; CNET depth+canny+hed stack</li></ul>Flux Lora CNET<ul><li>Flux txt2img/img2img with Lora &amp; CNET depth+cenny+hed stack</li></ul>Flux Enhance<ul><li>Flux Enhance</li><li>img2img enhancer, using Florence2 detailed caption conditioning</li></ul>V12Flux Scene Editor<ul><li>Scene Creator with image loading layers instead of generation.</li><li>faster, but requires images be made in advance (asset library)</li></ul>Flux Video Detailer<ul><li>intended to fix bad AI video details or blurring</li><li>denoises with boost, no upscale, tiled 320px</li><li>video to video</li></ul>Flux Live Portrait<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/539936">Loki-LivePortrait</a> method, with Flux bridge feeding the input</li><li>animates a generated image, with a talking video driver.</li></ul>Flux Mimic Motion<ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/539936">Loki-MimicMotion</a> method, with flux bridge feeding the input</li><li>animates a generated image, using a video input.</li></ul>V14Flux Lora Tester<ul><li>Creates two images with the exact same parameters for comparison</li><li>Lora ON vs Lora OFF</li><li>outputs all images save to sub folders by lora name</li><li>outputs specially formatted comparison image, (side by side split ON/OFF)</li></ul>Flux Lora Compare<ul><li>Load up to 8 Intermediate Lora models</li><li>Creates images with the exact same parameters for comparison</li><li>Lora Off output at the top for baseline</li><li>each stage can be toggled easily</li><li>outputs specially formatted comparison image, with Epoch labels</li><li>see demo images for this pack version</li></ul>V15Flux IP Adapter Basic<ul><li>uses the new Flux IPAdapter</li></ul>Flux IP Adapter Lora<ul><li>Adds Lora Stack to the workflow</li></ul>Flux IP Adapter Lora CNET<ul><li>Adds CNET to the workflow</li></ul>Compare versions<ul><li>all the above 3 IPA workflows</li><li>4 outputs (foda standard, IPA off &amp; two IPA stengths)</li><li>These 4 images create a presentation Grid for comparison</li></ul>V16Quality of Life Update (28 Workfows in Pack)<ul><li>re-organised Workflows by Function group</li></ul><ul><li>introduced "Easy Reroute" system for Model/Clip/VAE</li><li>allows easy connections to alternate Flux models (FP4/GGUF)</li></ul><ul><li>all previous workflows stored in /_archived/</li></ul>V17Foda Flux Nova Relighting<ul><li>generated image with flux CNET/Lora/IPA into Nova IC-Light</li><li>includes Foda Flux Animation Enhancer, special for detailing/upscale</li></ul>Foda Image Nova Relighting<ul><li>same as above, but faster, due to skipping generation, loading images instead</li><li>includes Foda Flux Animation Enhancer, special for detailing/upscale</li></ul>All packs include the previous versions, new workflows will be added as more capabilities are unlocked. When we reach V20, all workflows will be "refactored" to clean the pack up.<h3 id="you-will-need:-e9w96kbyg">You will need:</h3> CLIP <a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors?download=true">https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/clip_l.safetensors?download=true</a><a target="_blank" rel="ugc" href="https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors?download=true">https://huggingface.co/comfyanonymous/flux_text_encoders/resolve/main/t5xxl_fp8_e4m3fn.safetensors?download=true</a> place both inside ComfyUI/models/clip/VAEae.sft (old model, still works, now below as safetensors)or<a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors?download=true">https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/ae.safetensors?download=true</a>place inside ComfyUI/models/vae/Diffusion Model<a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/flux1-schnell.sft">https://huggingface.co/black-forest-labs/FLUX.1-schnell/resolve/main/flux1-schnell.sft</a>place inside ComfyUI/models/unet/New Comfy Checkpoint here:<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/flux1-schnell/resolve/main/flux1-schnell-fp8.safetensors?download=true">https://huggingface.co/Comfy-Org/flux1-schnell/resolve/main/flux1-schnell-fp8.safetensors?download=true</a>Schnell GGUF Models here: <a target="_blank" rel="ugc" href="https://huggingface.co/city96/FLUX.1-schnell-gguf/tree/main">https://huggingface.co/city96/FLUX.1-schnell-gguf/tree/main</a>(GGUF T5 text encoder here:) <a target="_blank" rel="ugc" href="https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/tree/main">https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/tree/main</a>many more configurations are possible, use the reroute system to connect whatever you wish to use !CONTROLNET<a target="_blank" rel="ugc" href="https://huggingface.co/XLabs-AI/flux-controlnet-collections/tree/main">https://huggingface.co/XLabs-AI/flux-controlnet-collections/tree/main</a>Flux Canny &amp; Depth V2 were released !Clip Vision L<a target="_blank" rel="ugc" href="https://huggingface.co/openai/clip-vit-large-patch14/tree/main">https://huggingface.co/openai/clip-vit-large-patch14/tree/main</a><a target="_blank" rel="ugc" href="https://huggingface.co/openai/clip-vit-large-patch14/blob/main/model.safetensors">clip_vision_l.safetensors</a>place inside ComfyUI/models/clip_vision/consider renaming to clip_vision_l.safetensorsIP ADAPTER<a target="_blank" rel="ugc" href="https://huggingface.co/XLabs-AI/flux-ip-adapter/tree/main">https://huggingface.co/XLabs-AI/flux-ip-adapter/tree/main</a> <a target="_blank" rel="ugc" href="https://huggingface.co/XLabs-AI/flux-ip-adapter/blob/main/flux-ip-adapter.safetensors">flux-ip-adapter.safetensors</a>place inside ComfyUI/models/xlabs/ipadapters/because IP Adapter is so new, the nodes may not be available yet: <a target="_blank" rel="ugc" href="https://github.com/XLabs-AI/x-flux-comfyui">https://github.com/XLabs-AI/x-flux-comfyui</a>but install just fine :) SAM2 Segment Anything<a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-segment-anything-2">https://github.com/kijai/ComfyUI-segment-anything-2</a> Florence2 LLM (prompt 2 mask)<a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-Florence2">https://github.com/kijai/ComfyUI-Florence2</a>LivePortrait or MimicMotion, setup instructions are here: <a target="_blank" rel="ugc" href="https://civarchive.com/models/539936">https://civarchive.com/models/539936</a>Kijai's FLUX1 Comfy Lora's <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/flux-loras-comfyui/tree/main/xlabs">https://huggingface.co/Kijai/flux-loras-comfyui/tree/main/xlabs</a>Faetastic Details Lora <a target="_blank" rel="ugc" href="https://civarchive.com/models/643886">https://civarchive.com/models/643886</a>Need LUT's in cube format for color correction?<a target="_blank" rel="ugc" href="https://fixthephoto.com/free-luts">https://fixthephoto.com/free-luts</a>

Foda FLUX Pack | txt2img/img2img, IP Adapter, Lora/CNET stack, Inpainting, Upscale, Relighting

adds Live Portrait, Mimic Motion &amp; Flux Video Detailer

Files with SHA256: 8a0fb6b449ef0e305a10209cecbd8a037f492ce44ede0b1f75ee9718ea60b515