Replace any background.
3.0
14 reviewsDescription
This ComfyUI workflow by #NeuraLunk uses Keyword prompted segmentation and masking to do controlnet guided outpainting around an object, person, animal etc. aso.
Flow-App instructions:
🔴 1. Upload a starting image of an object, person or animal etc. \n
🔴 2. Use one or two words to describe the object you want to keep.
🔴 3. Describe what you would want as a new background, start with the word(s) used in step 2. for best results!
🔴 Now press Press CREATE to see the result in a minute ! 💚
------------------
This workflow uses nodes for image loading, edge detection with Canny, latent space encoding for inpainting with VAEEncode, and applies neural control networks to guide the modifications. The workflow concludes with nodes to preview and save the generated image after the outpainting process
Discussion
(No comments yet)
Loading...
Reviews
No reviews yet
Versions (12)
- latest (5 months ago)
- v20240127-113618
- v20240127-104004
- v20240127-094615
- v20240126-194919
- v20240126-193225
- v20231212-170822
- v20231118-183920
- v20231118-143312
- v20231118-135750
- v20231118-134934
- v20231106-205513
Node Details
Primitive Nodes (9)
Note
Reroute
Seed (rgthree)
Text box
Custom Nodes (28)
- CheckpointLoaderSimpleWithNoiseSelect
- CM_NearestSDXLResolution
ComfyUI
- PreviewImage
- VAEEncode
- VAEDecode
- KSamplerAdvanced
- ControlNetApplyAdvanced
- CLIPTextEncode
- VAEEncodeForInpaint
- ImageScale
- CLIPSetLastLayer
- LoadImage
- SaveImage
- ControlNetLoaderAdvanced
- SAMModelLoader (segment anything)
- GroundingDinoModelLoader (segment anything)
- GroundingDinoSAMSegment (segment anything)
- InvertMask (segment anything)
- Image Canny Filter
- Text Concatenate
- Convert Masks to Images
Model Details
Checkpoints (1)
crystalClearXL_ccxl.safetensors
LoRAs (0)