<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a70d4d84-9d58-4e56-a0eb-70fe0f49f2be/original=true/a70d4d84-9d58-4e56-a0eb-70fe0f49f2be.jpeg" />Hey y'all! <span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Use familiar SDXL prompting to generate a character and pose separately, then place and relight that posed character onto an input background, all while maintaining character consistency and style! All without a character lora!<span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Special thanks to tori29umai (on<a target="_blank" rel="ugc" href="https://x.com/tori29umai"><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px"> Twitter</a><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">) for the charaBG and image2body loras, dx8152 (on <a target="_blank" rel="ugc" href="https://x.com/dx8152"><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Twitter</a><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px"> and <a target="_blank" rel="ugc" href="https://huggingface.co/dx8152"><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">Hugging Face</a><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">) for the Fusion lora and @DigitalPastel for SDXL workflows which portions of this one is based on.I made this workflow because my previous workflow lost too much style after RePosing a character. Also my other Fusion workflow's compositing part was waaay too clunky.Video Tutorial will be made eventually. This one needs it.[bideo lonk]Usage:<ul><li>Keyframes for video generation</li><li>Panels for comics</li><li>Material for training character loras</li><li>Memes! I dunno ~</li></ul>Notes:<ul><li>Read the notes</li><li>Download the models, which are all linked in the workflow.</li><li>Set the Cache Full File Path, otherwise it won't work!</li><li>Run the workflow ONE GROUP AT A TIME!</li><li>READ THE NOTES</li></ul>Here's a map of the workflow and what each active part does.Workflow Map:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ef986647-187c-48ce-8782-6223e7d4e806/original=true/ef986647-187c-48ce-8782-6223e7d4e806.jpeg" />Active Workflow Groups:<ul><li>SDXL Pose - Generates a dynamic character pose from prompts (optional with input pose image)</li><li>SDXL Character - Generates an idle standing character from prompts (optional with input character image)</li><li>Qwen Character Sheet - Generates a 4-view character sheet from the SDXL character</li><li>Qwen Pose - Extracts the pose mannequin from SDXL Pose</li><li>Qwen RePose - Reposes character to the Qwen Pose using the Character Sheet</li><li>SDXL Refine - Refines with SDXL prompts and loras to reinject SDXL style (optional)</li><li>Compositing - Removes background and places character onto background image</li><li>Qwen Fusion - Relights and casts shadows for the character in the scene.</li></ul>See example below:Info Sheet:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a7082266-7b8b-43e1-8cbd-18cd58046ba8/original=true/a7082266-7b8b-43e1-8cbd-18cd58046ba8.jpeg" />Character Sheet:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/14d0ab78-b4c6-49dd-a834-6c72ada2747e/original=true/14d0ab78-b4c6-49dd-a834-6c72ada2747e.jpeg" />All of these, except for the background image, are generated in this workflow.All intermediate images, ARE NOT, outputted by default. You can output the intermediate images by checking 'preview_only' to false.You can also fetch the most recent intermediate images from the cache folder.Version 1.2<ul><li>Added option and notes to load the Qwen Rapid All-in-One model, which can do NSFW stuff with the Qwen steps. Mostly works on the Qwen Fusion step.</li></ul>Version 1.1<ul><li>Added character and pose input images and switch. Allows you to skip either or both the SDXL pose and character groups.</li><li>Made the SDXL Refine group optional. You can run Qwen RePose then Qwen Fusion, skipping SDXL Refine.</li></ul>Version 1.0;<ul><li>Initial Release!</li><li>Takes prompts and a background image and generates a posed character onto that background image.</li></ul>Future variants &amp; planned workflows:<ul><li>A variant with a pose input images, to aid generating the pose via Control Net.</li><li>A pose input image, use pose ref images to control poses for your generated character.(ADDED)</li><li>A character input image, use SDXL to generate poses for an existing character. (ADDED)</li><li>Versions of all those above, with the compositing group removed. Similar to Lazy RePose.</li><li>A separate bigger compositing workflow, for multiple character and prop placement.</li><li>NSFW versions!</li></ul>This workflow is time-consuming to run, but once you've got a character going, you can pose that character in almost any way. The RePose part will fail if the pose is too complex. SDXL refine brings back a lot of the style that is lost in Qwen, but its also not perfect.Regardless, I achieved 90% of what I wanted, and it will serve as a great base for future workflow variants.Anyhow, enjoy the workflow. Please post if you have any questions or suggestions!Stay Cheesy Y'all!~<ul><li>Brie Wensleydale</li></ul>PS. Please, if you see something that could be improved, please tell me! Much appreciated!

Brie's Advanced Character Fusion

About this versionAdded a separate checkpoint loader for the AIO model. So now you can do NSFW things in the Qwen steps. Although still not that well.

Brie_Qwen_Adv_Char_Fusion_Base_v002.json

v2.0 Base

v1.2 Base

v1.0 Base

v1.1 Updated with image input options for both the character and pose parts. Thus meaning you can skip both initial SDXL portions.I have also made the SDXL refiner step, optional. The workflow will function if you skip that step. Kinda defeats the whole purpose of the workflow, but the option is there for more flexibility.v 1.2 Also Added option and notes to load the Qwen Rapid AIO model for NSFW option for Qwen steps.

Files with SHA256: 006ccd0717d93b2ec997ab09dbc9d612b3efca9d5ec73cf5b47ac487f3de9789