She has depth

控制网深度

Youtube： https://www.youtube.com/watch?v=OnwNcxJwYQE

crie personagens antropomórficos com rosto de uma ser humano normal, porem apenas o corpo mudado, com profundidade de pelo, distinguir partes que serão encobertas por pelos etc.

### Redux Background and Character Replacement Process### I. Workflow Process Description:1. Extract the Character: the character from the original background.2. Position the Character: Place the extracted character proportionally onto the designated masked area. Next, perform depth redrawing on the pre-composited image: 3. Load the Flux Depth Model: Access the model necessary for depth processing. 4. Extract the Depth Map: Create and consolidate the depth map of the composited image for redrawing. 5. Generate the Redrawing Prompt: Derive a prompt that will guide the redrawing process. 6. Control Facial Features: Adjust the character's facial features using Pulid. 7. Apply Redux to the Background: Integrate Redux effects on the background. 8. Apply Redux to the Character: Apply Redux effects to the character. 9. Sample and Generate Final Image: Produce the final image based on the adjustments made.### II. Usage Instructions:1. Upload Character Image: Ensure the character image is clear and complete, particularly focusing on a large facial region.2. Upload Background Image: Add the desired background in the designated area.3. Paint a Mask on the Background: Simply paint a mask up and down; the left and right areas will adjust automatically.### III. Parameter Adjustment Instructions:1. Adjust Facial Similarity: Change the weight of Pulid to modify the similarity of the character's face.2. Adjust Background Similarity: Alter the `downsampling_factor` in the Redux background area; a value of 1 represents the strongest and most similar effect, while a value of 3 indicates the weakest effect with the greatest change.3. Adjust Other Character Areas: Modify the `downsampling_factor` in the Redux character area similarly; again, a setting of 1 is the strongest and most similar, while 3 is the weakest.

Flux Depth & Canny Tools (Integrated ControlNets)In this workflow and guide we'll use the official Black Forest Labs' Flux Tools Depth and Canny, more commonly referred to as ControlNet models. But these are not standalone ControlNet models. Canny/Depth are integrated into the Flux base model, hence the name Flux Tools and technically not being ControlNet models (even though they act very similar).The workflow to load these tools are also different from older generations like Stable Diffusion ControlNets. We're instead starting the generation with the Canny/Depth model to finish the generation with the Flux dev base model (without Canny/Depth).Models neededFlux Dev FP8: https://huggingface.co/Kijai/flux-fp8/tree/mainFlux Dev Canny FP8: https://civitai.com/models/995751/flux1-canny-dev-fp8-e4m3fnFlux Dev Depth FP8: https://civitai.com/models/991221Place in \ComfyUI\models\diffusion_models\t5xxl_fp8 (available in model manager): https://huggingface.co/comfyanonymous/flux_text_encoders/tree/mainclip_l.safetensors https://huggingface.co/comfyanonymous/flux_text_encoders/tree/mainPlace in \ComfyUI\models\clip\ae.safetensors: https://huggingface.co/black-forest-labs/FLUX.1-dev/tree/mainPlace in \ComfyUI\models\vae\Load the workflow by dragging & dropping it into your ComfyUIInstall any missing nodes from the Manager

lora strength 0.6-1.Trigger keywords are wanostyle (mandatory) and monkey d luffy for Luffy or roronoa zoro for Zoro. May also get nami and nico robin without embeddings. Luffy prompts reference:1boy, wanostyle, monkey d luffy, smiling, straw hat, looking at viewer, solo, upper body, ((masterpiece)), (best quality), (extremely detailed), depth of field, sketch, dark intense shadows, sharp focus, soft lighting, hdr, colorful, good composition, fire all around, spectacular, closed shirt, anime screencap, scar under eye, ready to fight, black eyes Zoro prompt word reference: 1boy, wanostyle, roronoa zoro, angry looking, katana, (one eye closed), scar across eye, solo, upper body, (((masterpiece))), ((best quality)), (extremely detailed), watercolor, illustration, depth of field, sketch, dark intense shadows, sharp focus, soft lighting, hdr, colorful, good composition, purple fire all around, spectacular, green hair, Nami prompt word reference: 1girl, wanostyle, nami_1800, (masterpiece), (best quality), solo, female focus, extremely detailed, illustration, kimono, traditional clothing, depth of field, sketch, dark intense shadows, sharp focus, soft lighting, colorful, good composition, solo, indoors,

What this workflow does a workflow for creating an image with a depth perspective effect using IPAdapters. This image can be animated using Stable Video Diffusion to produce a ping pong video with a 3D or volumetric appearance. All of this in the same workflow. How to use this workflow You will need to use a mask image with three stacked layers, green blue and red (check examples). Then you can use three input image to be adapted in these three regions. This is used to create the composition, specifically the foreground and the central part. It's important to create an image with a convincing depth perspective, as the quality of the final video depends on it. Tips about this workflow Before running the full workflow, bypass the Ksampler node in the Video group, so that you can check if the image to animate looks good first. Also, you might need to find the right motion_bucket_id and seed to generate the proper camera pan, it might change depending on the depth of the input image. You can download an example mask and input images in the workflow-inputs.zip: https://civitai.com/articles/3235/a-workflow-for-depthparallax-images-and-videos-using-ipadapters-and-stable-video-diffusion

Important: All versions of V1, V2 and V3 can be downloaded by clicking the buttons on the right. From top to bottom are V3, V2, V1. If your project requires relighting capabilities, please use Flux Background Replacer V2, as Flux Background Replacer V3 does not include this feature. Below is a detailed comparison to help you understand the key differences between the two workflows: Key Differences Between ‘Flux Background Replacer V2’ and ‘Flux Background Replacer V3’: Node Count and Complexity: Flux Background Replacer V2: A highly complex workflow featuring over 108 nodes, ideal for scenarios where precise image manipulation and blending are essential. Flux Background Replacer V3: With a more streamlined design, V3 contains 80 nodes, providing a simpler and more efficient workflow without compromising on quality. ControlNet Model and Edge Handling: Flux Background Replacer V2: Utilizes the ControlNet Canny model from Xlabs, which is specifically designed for advanced edge detection and outline preservation. This, combined with its relighting function, allows for photorealistic integration of subjects into the new background. Flux Background Replacer V3: Uses the ControlNet Depth model and Upscaler model from Jasper AI, optimized to control edges and outlines without the need for additional specialized nodes. This makes it easy to use the ‘Apply ControlNet’ node, saving time and simplifying setup.

"Fotografía de ambiente realista en pequeña cafetería de playa. Barista carismática, sonrisa relajada, cabello medio largo con rasurado lateral, piel dorada por el sol, prepara un café helado con máquina profesional. Atuendo: shorts vaqueros ajustados y top sin mangas holgado sobre sujetador de , figura esbelta. Composición amplia mostrando la barra de madera desgastada, estanterías llenas de granos y vasos, máquina de hielo, fondo desenfocado con sombrillas de playa y mar turquesa bajo un sol radiante. Profundidad de campo muy reducida, bokeh suave y dorado. Estilo documental de alta gama, detalles impecables en luces y sombras."hotograph of victorian woman with wings, sky clouds, meadow grass

Youtube： https://www.youtube.com/watch?v=LuLh22WdQqw