Ling-APE / ComfyUI-All-in-One-FluxDev-Workflow

An All-in-One FluxDev workflow in ComfyUI that combines various techniques for generating images with the FluxDev model, including img-to-img and text-to-img. This workflow can use LoRAs, ControlNets, enabling negative prompting with Ksampler, dynamic thresholding, inpainting, and more.
182 stars 8 forks source link

nice work! add Video Gen #9

Open tqangxl opened 2 months ago

tqangxl commented 2 months ago

nice work!!!!! 1.add automatically saves an extra image in JPG and stripped of all metadata for share, 2.Uploader function allows to iteratively load the 1st reference image and the 2nd reference image from a source folder. This is particularly useful to process a large number of images without the limitations of a batch 3.two extra functions: FLUX ControlNet Tile and FLUX ControlNet Pose, enabled by the InstantX ControlNet Union Pro model 4.The Inpainter and Repainter (img2img) functions use FLUX as default model 5.supports the new ControlNet Canny, Depth, and HED models for FLUX,supports FLUX Model Sampling

  1. LUT Applier function, useful to apply a Look Up Table (LUT) to an uploaded or generated image.
  2. Color Corrector function, useful to modify gamma, contrast, exposure, hue, saturation, etc. of an uploaded or generated image
  3. Grain Maker function, useful to apply film grain to an uploaded or generated image
  4. ref. The Upscaler (SUPIR) function now automatically generates a caption for the source image to upscale via a dedicated Florence-2 node
  5. The Inpainter without Mask function you can called Repainter (img2img)
  6. Power Lora Loader node in the LoRAs function
  7. add Controller to enable or disable functions
  8. ref workflow workflow----.json