<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/VnqXiCMa5a0" start="0"></iframe></div><h1 id="sd3-control-net-update!-5a42t3u93">SD3 Control Net update!</h1>much information and tips on the settings are in the video :D <ul><li>Canny, Pose and Tile - updated the pack with four new workflows.</li><li>txt2img with controlnets</li><li>img2img with controlnets</li><li>&amp; Blip Auto Prompt versions of both</li></ul>You will Need: <a target="_blank" rel="ugc" href="https://huggingface.co/InstantX/SD3-Controlnet-Canny">https://huggingface.co/InstantX/SD3-Controlnet-Canny</a><a target="_blank" rel="ugc" href="https://huggingface.co/InstantX/SD3-Controlnet-Pose">https://huggingface.co/InstantX/SD3-Controlnet-Pose</a><a target="_blank" rel="ugc" href="https://huggingface.co/InstantX/SD3-Controlnet-Tile">https://huggingface.co/InstantX/SD3-Controlnet-Tile</a>place inside /models/controlnet/SD3/<h1 id="sd3-is-here!-3tmhzuop5">SD3 is here!</h1>installation / explanation (pack v1 video)<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/aGogZsFqgSI" start="0"></iframe></div><h3 id="the-latest-non-commercial-image-generation-model-has-arrrivedsimply-download-the-weights-here:https:huggingface.costabilityaistable-diffusion-3-mediumtreemain-bozl98k46">the latest non-commercial image generation model has arrrived simply download the weights here: <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3-medium/tree/main">https://huggingface.co/stabilityai/stable-diffusion-3-medium/tree/main</a></h3> 10.6 GB <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips_t5xxlfp8.safetensors">sd3_medium_incl_clips_t5xxlfp8.safetensors - contains all 3 encoders, T5 in FP8</a> 15.8 GB <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips_t5xxlfp16.safetensors">sd3_medium_incl_clips_t5xxlfp16.safetensors - contains all 3 encoders, T5 is FP16</a> 5.97 GB <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium_incl_clips.safetensors">sd3_medium_incl_clips.safetensors - contains only CLIP G+L</a> 4.34 GB <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3-medium/blob/main/sd3_medium.safetensors">sd3_medium.safetensors - contains no text encoders in the checkpoint.</a>you can choose to load the CLIP text encoders separately, if you download them to your models/CLIP/ folder. The weights are here: <a target="_blank" rel="ugc" href="https://huggingface.co/stabilityai/stable-diffusion-3-medium/tree/main">https://huggingface.co/stabilityai/stable-diffusion-3-medium/tree/main</a><img src="https://i.gyazo.com/12b2519e4a28ea56aafed0523e7f3ca2.png" /><h1 id="!-update-comfyui-!-87i08aiib">! UPDATE COMFYUI !</h1> Update: 16th June: adds image 2 image workflow Pack contains 3 workflows: SD3-HYPER-SUPIR- SD3-medium- 1MP aspect ratio modulo 64- random line for batch prompting- lora loader (chaotic)- Triple Clip Encode- 4K 16:9 Hyper SUPIR upscalingAlthough SDXL Lora do have an effect on generation (G+L), they are not guiding toward the trained tokens.SD3 supports multi line prompting so the "random line" batch prompting is disabled by default.<img src="https://i.gyazo.com/47e96402e99d4cb89ca83b6a3c6a08e4.png" />SD3-HYPER-SUPIR-Reactor- adds Reactor Restore FaceSD3-img2img-HYPER-SUPIR- adds img2img - basic version features less custom nodes Reactor version allows Facefix, not faceswap, although that can be added.

SD3 Pack - txt2img, img2img, 4K Upscaling

used SDXL hyper for the SUPIR upscaling only

Files with SHA256: b8aedc2bf0e23b1cb8919875b651cbb59857b55825be6a1e39ad68a302324183