Add five useful FLUX workflows

2026-08-08 20:44:12 +00:00
parent 1c577ae514
commit 61123d4923
12 changed files with 7521 additions and 0 deletions
@@ -0,0 +1,54 @@
+# Flux Redux Reference Restyle
+
+## Summary
+
+Reference-image restyling / variation workflow using `Flux Redux`. This is more useful than plain text-to-image because it starts from one or more real image cues and pushes them into new outputs.
+
+## Model Family
+
+- `flux`
+
+## Status
+
+- `imported-only`
+
+## Source
+
+- Original repo page: <https://huggingface.co/StableDiffusionVN/Flux>
+- Workflow file: <https://huggingface.co/StableDiffusionVN/Flux/resolve/main/ComfyUI_workflow/Flux_Redux.json>
+- Related public workflow listing: <https://comfy.org/workflows/flux_redux_model_example-52dd3f09bb59/>
+- Original publisher: `StableDiffusionVN`
+- Date imported: `2026-08-08`
+
+## Developer notes
+
+- The publisher includes this as one of the example FLUX workflows in their model repo.
+- Their README provides the workflow file directly but does not add much hand-holding beyond the download links and a few related node references.
+- The public workflow listing describes it as using Flux Redux to generate image variants by transferring style from reference imagery.
+
+## Our notes
+
+- This is one of the more interesting "useful not flashy" FLUX workflows because reference-guided variation is an actual production use case.
+- Good fit when you want to keep composition or visual DNA from a source image while pushing the result toward a new look.
+- Simpler dependency surface than the all-in-one graph.
+
+## Required custom nodes
+
+- `StyleModelLoader`
+- `StyleModelApply`
+
+These may come from your existing FLUX / Comfy build depending on version, but if they do not, expect to install the matching style-model support used by the source workflow.
+
+## Built-in / core nodes used
+
+- `CheckpointLoaderSimple`
+- `CLIPVisionLoader`
+- `CLIPVisionEncode`
+- `CLIPTextEncode`
+- `KSampler`
+- `VAEDecode`
+
+## Notes
+
+- Best use: style transfer, guided variation, and reference-led experimentation.
+- This is not the most node-heavy workflow here, which makes it a decent first import after the basic setup is stable.