chris.dumas/comfyui-workflows
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add five useful FLUX workflows

Browse Source
This commit is contained in:
Morpheus
2026-08-08 20:44:12 +00:00
parent 1c577ae514
commit 61123d4923
12 changed files with 7521 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models/flux/README.md
+14
View File
@@ -0,0 +1,14 @@
# FLUX Workflows
Use this folder for general `FLUX` family workflows that are not specifically `FLUX.2-klein` only.
Good candidates here:
- inpaint / outpaint
- reference-image restyling
- ControlNet or Union ControlNet pipelines
- upscale or detail-recovery workflows
- image-to-image or hybrid editing pipelines
- multi-tool "all in one" workflow packs
Store each workflow in its own subfolder.
models/flux/all-in-one-fluxdev-v0-2/README.md
+63
View File
@@ -0,0 +1,63 @@
# All-in-One FluxDev v0.2
## Summary
Large multi-purpose `FLUX.1-dev` workflow that combines text-to-image, image-to-image, LoRA loading, ControlNet, negative-prompt-style experimentation, simple inpainting, and iterative upscale/detailing in one graph.
## Model Family
- `flux`
## Status
- `imported-only`
## Source
- Original page: <https://github.com/Ling-APE/ComfyUI-All-in-One-FluxDev-Workflow>
- Workflow file: <https://raw.githubusercontent.com/Ling-APE/ComfyUI-All-in-One-FluxDev-Workflow/main/All-in-One-FluxDev-v0.2.json>
- Original author: `Ling-APE`
- Date imported: `2026-08-08`
## Developer notes
- The author describes this as a personal "all in one" interpretation rather than the single correct way to use FLUX.
- The workflow leans heavily on `Use Everywhere` nodes to keep a large graph manageable.
- It supports switching between text-to-image and image-to-image, optional ControlNet and LoRA loading, two different sampling approaches, simple inpainting, and a high-res fix style upscale path.
- The author notes that the included XLabs ControlNet tests worked best with minimal prompting, square-ish setups, and guidance around `4`.
- A converted ComfyUI-friendly version of the XLabs realism LoRA is recommended by the author.
- The repo also mentions optional Ollama + Florence2 helpers for captioning and prompt assistance.
## Our notes
- This is the most feature-rich import in the current `flux` folder, but it is also the messiest dependency-wise.
- Good candidate when you want one workflow to dissect and mine for ideas rather than the cleanest daily-driver graph.
- If you only want one FLUX workflow that covers a lot of territory, this is the most "toolbox" option of the five.
- Expect node drift over time because it pulls from several custom packs and a 2024-era FLUX experimentation stack.
## Required custom nodes
- `cg-use-everywhere` / `Use Everywhere`
- `ComfyUI-Inspire-Pack`
- `ComfyUI-Impact-Pack`
- `ComfyUI-TiledDiffusion`
- `ComfyUI-Florence2`
- `comfyui-ollama`
- `rgthree-comfy`
- `pysssss` custom scripts
- `ComfyUI-Crystools`
- `ComfyUI-PixelResolutionCalculator`
- likely `ComfyUI-KJNodes` or equivalent schedule-hook providers used by the upscale section
## Built-in / core nodes used
- FLUX guidance and sampling nodes
- UNET / VAE / CLIP loaders
- ControlNet loader/apply
- LoRA loader
- VAE encode/decode
## Notes
- Best use: hybrid experimentation, not a minimal clean import.
- If missing-node resolution gets annoying, start with the simpler workflows in this repo first and come back to this one later.
models/flux/all-in-one-fluxdev-v0-2/workflow.json
+6473
View File
File diff suppressed because it is too large Load Diff
models/flux/flow-upscaler/README.md
+50
View File
@@ -0,0 +1,50 @@
# Flow Upscaler
## Summary
Fast latent upscaler for the `FLUX.2` family. It takes existing FLUX latents and upscales them in latent space, so you can push images much larger without relying only on classic pixel upscalers.
## Model Family
- `flux`
## Status
- `imported-only`
## Source
- Original page: <https://github.com/tensorforger/comfyui-flow-upscaler>
- Workflow file: <https://raw.githubusercontent.com/tensorforger/comfyui-flow-upscaler/main/workflow.json>
- Original author: `TensorForger`
- Date imported: `2026-08-08`
## Developer notes
- The author positions this as a fast latent upscaler trained in `Flux.2` latent space.
- The model is trained for `2x` upscaling, but multiple passes can be chained for much larger outputs.
- The README recommends the tiny `Flux.2` VAE (`taef2`) for `2048x2048` and above because the original VAE becomes impractical at high resolutions.
- The workflow included in the repo is the demo path the author expects people to load first.
## Our notes
- This is one of the most practically useful imports here because it solves a real workflow problem instead of just offering another generation variant.
- It looks especially relevant if you end up using `FLUX.2-klein` or other lighter FLUX-family generation paths and want cleaner high-res finishing.
- It is more specialized than a generic Ultimate SD Upscale graph, which is a good thing if you want something clearly tied to the FLUX latent stack.
## Required custom nodes
- `comfyui-flow-upscaler`
- `rgthree-comfy` for `Image Comparer`
## Built-in / core nodes used
- `Flux2Scheduler`
- `EmptyFlux2LatentImage`
- standard CLIP / UNET / VAE loaders
- sampler selection and advanced sampler nodes
## Notes
- Model weights are separate from this workflow and need to be downloaded from the source repo's linked Hugging Face page.
- Best use: upscale a good FLUX-family image after the composition is already right.
models/flux/flow-upscaler/workflow.json
+1
View File
File diff suppressed because one or more lines are too long
models/flux/flux-fill-inpainting/README.md
+47
View File
@@ -0,0 +1,47 @@
# Flux Fill Inpainting
## Summary
Focused FLUX fill workflow for inpainting and outpainting, with emphasis on lower-VRAM usage through the companion custom node pack.
## Model Family
- `flux`
## Status
- `imported-only`
## Source
- Original page: <https://github.com/rubi-du/ComfyUI-Flux-Inpainting>
- Workflow file: <https://raw.githubusercontent.com/rubi-du/ComfyUI-Flux-Inpainting/main/workflow/inpainting.json>
- Original author: `rubi-du`
- Date imported: `2026-08-08`
## Developer notes
- The repo wraps FLUX fill as ComfyUI nodes and explicitly pitches lower-VRAM inpaint/outpaint usage compared with the heavier default FLUX fill route.
- The maintainer later added `FluxSimpleInpainting`, `FluxTransformerInpainting`, and `FluxGuffInpainting` variants, but this import is the plain `Flux Inpainting` example workflow.
- The project README points people to ComfyUI Manager install or a manual `requirements.txt` install.
- The author also documents split-pipeline variants and VAE / GGUF-specific loading options in the same repo.
## Our notes
- This is the cleanest dedicated editing workflow in the set.
- It is a better "do one thing well" import than the giant all-in-one graph if your main interest is object replacement, cleanup, or extending an image.
- If FLUX editing ends up mattering more to you than FLUX prompt generation, this is one of the first ones worth trying.
## Required custom nodes
- `ComfyUI-Flux-Inpainting`
## Built-in / core nodes used
- `LoadImage`
- `PreviewImage`
## Notes
- This specific workflow is tiny, but the custom node repo behind it is the real dependency.
- Good starting point for a future branch where we also import the repo's `FluxSimpleInpainting` or `FluxGuffInpainting` variants.
models/flux/flux-fill-inpainting/workflow.json
+164
View File
@@ -0,0 +1,164 @@
{
"last_node_id": 18,
"last_link_id": 22,
"nodes": [
{
"id": 13,
"type": "PreviewImage",
"pos": {
"0": 1323,
"1": -719
},
"size": {
"0": 660.6964111328125,
"1": 434.039794921875
},
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 12,
"label": "images"
}
],
"outputs": [],
"properties": {
"Node name for S&R": "PreviewImage"
},
"widgets_values": []
},
{
"id": 10,
"type": "Flux Inpainting",
"pos": {
"0": 1220,
"1": -1000
},
"size": {
"0": 400,
"1": 200
},
"flags": {},
"order": 1,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 21,
"label": "image"
},
{
"name": "mask",
"type": "MASK",
"link": 22,
"label": "mask"
}
],
"outputs": [
{
"name": "image",
"type": "IMAGE",
"links": [
12
],
"slot_index": 0,
"label": "image"
}
],
"properties": {
"Node name for S&R": "Flux Inpainting"
},
"widgets_values": [
"a cat",
50,
false,
30
]
},
{
"id": 11,
"type": "LoadImage",
"pos": {
"0": 545,
"1": -714
},
"size": {
"0": 640.788330078125,
"1": 436.8089294433594
},
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
21
],
"slot_index": 0,
"label": "IMAGE"
},
{
"name": "MASK",
"type": "MASK",
"links": [
22
],
"slot_index": 1,
"label": "MASK"
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"yosemite_inpaint_example.png",
"image"
]
}
],
"links": [
[
12,
10,
0,
13,
0,
"IMAGE"
],
[
21,
11,
0,
10,
0,
"IMAGE"
],
[
22,
11,
1,
10,
1,
"MASK"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.7400249944258223,
"offset": [
-387.7463295635271,
1057.1100176571422
]
}
},
"version": 0.4
}
models/flux/flux-redux-reference-restyle/README.md
+54
View File
@@ -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.
models/flux/flux-redux-reference-restyle/workflow.json
+1
View File
@@ -0,0 +1 @@
{"last_node_id":83,"last_link_id":127,"nodes":[{"id":71,"type":"CLIPVisionEncode","pos":[695,371],"size":[432.5999755859375,46],"flags":{},"order":5,"mode":0,"inputs":[{"name":"clip_vision","type":"CLIP_VISION","link":115},{"name":"image","type":"IMAGE","link":116}],"outputs":[{"name":"CLIP_VISION_OUTPUT","type":"CLIP_VISION_OUTPUT","links":[117],"slot_index":0}],"properties":{"Node name for S&R":"CLIPVisionEncode"},"widgets_values":[]},{"id":72,"type":"CLIPVisionLoader","pos":[352,371],"size":[315,58],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"CLIP_VISION","type":"CLIP_VISION","links":[115]}],"properties":{"Node name for S&R":"CLIPVisionLoader"},"widgets_values":["siglip-so400m-patch14-384.safetensors"]},{"id":73,"type":"LoadImage","pos":[350,479],"size":[315,314],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[116]},{"name":"MASK","type":"MASK","links":null}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["Art_wall.jpeg","image"]},{"id":74,"type":"StyleModelApply","pos":[1163,371],"size":[447,66],"flags":{},"order":7,"mode":0,"inputs":[{"name":"conditioning","type":"CONDITIONING","link":120},{"name":"style_model","type":"STYLE_MODEL","link":118},{"name":"clip_vision_output","type":"CLIP_VISION_OUTPUT","link":117}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[121,122],"slot_index":0}],"properties":{"Node name for S&R":"StyleModelApply"},"widgets_values":[]},{"id":75,"type":"StyleModelLoader","pos":[812,468],"size":[315,58],"flags":{},"order":2,"mode":0,"inputs":[],"outputs":[{"name":"STYLE_MODEL","type":"STYLE_MODEL","links":[118]}],"properties":{"Node name for S&R":"StyleModelLoader"},"widgets_values":["flux1-redux-dev.safetensors"]},{"id":76,"type":"CheckpointLoaderSimple","pos":[812,571],"size":[315,98],"flags":{},"order":3,"mode":0,"inputs":[],"outputs":[{"name":"MODEL","type":"MODEL","links":[127],"slot_index":0},{"name":"CLIP","type":"CLIP","links":[119],"slot_index":1},{"name":"VAE","type":"VAE","links":[126]}],"properties":{"Node name for S&R":"CheckpointLoaderSimple"},"widgets_values":["Checkpoint/Flux_dev_v1-fp8.safetensors"]},{"id":77,"type":"CLIPTextEncode","pos":[1167,513],"size":[443,182],"flags":{},"order":6,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":119}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[120],"slot_index":0}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":[""]},{"id":78,"type":"KSampler","pos":[1633,371],"size":[327,488],"flags":{},"order":8,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":127},{"name":"positive","type":"CONDITIONING","link":121},{"name":"negative","type":"CONDITIONING","link":122},{"name":"latent_image","type":"LATENT","link":123}],"outputs":[{"name":"LATENT","type":"LATENT","links":[124],"slot_index":0}],"properties":{"Node name for S&R":"KSampler"},"widgets_values":[800893977503502,"randomize",20,1,"euler","simple",1]},{"id":79,"type":"EmptyLatentImage","pos":[1290,766],"size":[315,106],"flags":{},"order":4,"mode":0,"inputs":[],"outputs":[{"name":"LATENT","type":"LATENT","links":[123]}],"properties":{"Node name for S&R":"EmptyLatentImage"},"widgets_values":[1024,1024,1]},{"id":80,"type":"VAEDecode","pos":[1978,371],"size":[210,46],"flags":{},"order":9,"mode":0,"inputs":[{"name":"samples","type":"LATENT","link":124},{"name":"vae","type":"VAE","link":126}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[125],"slot_index":0}],"properties":{"Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":81,"type":"SaveImage","pos":[2218.828369140625,371],"size":[391,485],"flags":{},"order":10,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":125}],"outputs":[],"properties":{"Node name for S&R":"SaveImage"},"widgets_values":["ComfyUI"]},{"id":83,"type":"Note","pos":[814,741],"size":[336,126],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[],"properties":{"text":""},"widgets_values":["Flux Redux\n\nComfyUI Colab:\n- Creator: stablediffusion.vn\n- Website: sdvn.me | comfy.vn | fluxai.vn\n- Sub Web: trainlora.vn | shakker.vn\n- Document: bit.ly/sdvn-lib\n- Skills training: hungdiffusion.com"],"color":"#432","bgcolor":"#653"}],"links":[[75,10,0,8,1,"VAE"],[76,12,0,44,0,"MODEL"],[77,11,0,48,0,"CLIP"],[78,10,0,30,1,"VAE"],[79,12,0,51,0,"MODEL"],[80,11,0,51,1,"CLIP"],[81,10,0,51,2,"VAE"],[115,72,0,71,0,"CLIP_VISION"],[116,73,0,71,1,"IMAGE"],[117,71,0,74,2,"CLIP_VISION_OUTPUT"],[118,75,0,74,1,"STYLE_MODEL"],[119,76,1,77,0,"CLIP"],[120,77,0,74,0,"CONDITIONING"],[121,74,0,78,1,"CONDITIONING"],[122,74,0,78,2,"CONDITIONING"],[123,79,0,78,3,"LATENT"],[124,78,0,80,0,"LATENT"],[125,80,0,81,0,"IMAGE"],[126,76,2,80,1,"VAE"],[127,76,0,78,0,"MODEL"]],"groups":[],"config":{},"extra":{"ds":{"scale":0.7060367454068242,"offset":[42.26144284386624,109.5583323652417]}},"version":0.4}
models/flux/flux-union-controlnet/README.md
+51
View File
@@ -0,0 +1,51 @@
# Flux Union ControlNet
## Summary
Control-guided FLUX workflow using Union ControlNet, aimed at steering generation from structural inputs rather than relying only on prompting.
## 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_Union_Controlnet.json>
- Original publisher: `StableDiffusionVN`
- Date imported: `2026-08-08`
## Developer notes
- The publisher lists this as one of the included FLUX example workflows in the same repo as their other ComfyUI examples.
- Their README specifically points to `ComfyUI-eesahesNodes` for InstantX / Union ControlNet support.
- The workflow uses an `AIO_Preprocessor`, so the source expects an installed preprocessor stack as well, not just the loader node.
## Our notes
- This is one of the more practically valuable FLUX workflows because structural control tends to matter more than raw prompting once you actually want repeatability.
- Good candidate if you care about pose, edges, or scene layout staying closer to plan.
- In practice this is the workflow I would keep around when "make it obey the source shape" matters more than style exploration.
## Required custom nodes
- `ComfyUI-eesahesNodes` for `InstantX Flux Union ControlNet Loader`
- a ControlNet preprocessor pack that provides `AIO_Preprocessor`, commonly `comfyui_controlnet_aux`
## Built-in / core nodes used
- `CheckpointLoaderSimple`
- `ControlNetApplySD3`
- `CLIPTextEncode`
- `KSampler`
- `LoadImage`
- `VAEDecode`
## Notes
- Best use: structure-aware FLUX generation, especially when you have edge/depth/pose style guidance.
- This is more useful than plain text-to-image because it pushes FLUX into controlled generation rather than prompt-only luck.
models/flux/flux-union-controlnet/workflow.json
+601
View File
@@ -0,0 +1,601 @@
{
"last_node_id": 62,
"last_link_id": 158,
"nodes": [
{
"id": 6,
"type": "CLIPTextEncode",
"pos": [
403,
148
],
"size": {
"0": 422.84503173828125,
"1": 164.31304931640625
},
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "clip",
"type": "CLIP",
"link": 156
}
],
"outputs": [
{
"name": "CONDITIONING",
"type": "CONDITIONING",
"links": [
119,
145
],
"slot_index": 0
}
],
"title": "CLIP Text Encode (Positive Prompt)",
"properties": {
"Node name for S&R": "CLIPTextEncode"
},
"widgets_values": [
"The image features a young woman standing on a sandy beach, with the ocean stretching out into the horizon behind her. She is dressed in a delicate, white spaghetti-strap top adorned with subtle floral patterns, which exudes an aura of simplicity and elegance. Her dark hair is styled in a low bun, accented by two white flowers, which add a touch of natural beauty to her serene appearance. The soft sunlight highlights her refined features, casting gentle shadows and enhancing the luminous quality of her skin. The gentle breeze catching stray strands of her hair contributes to the portrait's overall sense of tranquility and quiet reflection amidst the expansive, unspoiled beachfront. This composition effectively juxtaposes the calm presence of the woman against the vast, dynamic backdrop of the sea and sand."
]
},
{
"id": 8,
"type": "VAEDecode",
"pos": [
1508,
163
],
"size": {
"0": 210,
"1": 46
},
"flags": {},
"order": 9,
"mode": 0,
"inputs": [
{
"name": "samples",
"type": "LATENT",
"link": 143
},
{
"name": "vae",
"type": "VAE",
"link": 158
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
9
],
"slot_index": 0
}
],
"properties": {
"Node name for S&R": "VAEDecode"
}
},
{
"id": 51,
"type": "KSampler",
"pos": [
1178,
159
],
"size": {
"0": 315,
"1": 474
},
"flags": {},
"order": 8,
"mode": 0,
"inputs": [
{
"name": "model",
"type": "MODEL",
"link": 155
},
{
"name": "positive",
"type": "CONDITIONING",
"link": 144
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 146
},
{
"name": "latent_image",
"type": "LATENT",
"link": 140
}
],
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
143
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "KSampler"
},
"widgets_values": [
723469965151993,
"randomize",
20,
1,
"euler",
"simple",
1
]
},
{
"id": 50,
"type": "AIO_Preprocessor",
"pos": [
495,
365
],
"size": {
"0": 315,
"1": 82
},
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "image",
"type": "IMAGE",
"link": 151
}
],
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
136,
152
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "AIO_Preprocessor"
},
"widgets_values": [
"DepthAnythingV2Preprocessor",
1024
]
},
{
"id": 59,
"type": "PreviewImage",
"pos": [
849,
419
],
"size": {
"0": 295.18359375,
"1": 299.61328125
},
"flags": {},
"order": 6,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 152
}
],
"properties": {
"Node name for S&R": "PreviewImage"
}
},
{
"id": 9,
"type": "SaveImage",
"pos": [
1731,
160
],
"size": {
"0": 472.26861572265625,
"1": 537.8684692382812
},
"flags": {},
"order": 10,
"mode": 0,
"inputs": [
{
"name": "images",
"type": "IMAGE",
"link": 9
}
],
"properties": {
"Node name for S&R": "SaveImage"
},
"widgets_values": [
"ComfyUI"
]
},
{
"id": 52,
"type": "EmptyLatentImage",
"pos": [
493,
625
],
"size": {
"0": 315,
"1": 106
},
"flags": {},
"order": 0,
"mode": 0,
"outputs": [
{
"name": "LATENT",
"type": "LATENT",
"links": [
140
],
"shape": 3
}
],
"properties": {
"Node name for S&R": "EmptyLatentImage"
},
"widgets_values": [
768,
1152,
1
]
},
{
"id": 38,
"type": "ControlNetApplySD3",
"pos": [
841,
156
],
"size": {
"0": 315,
"1": 186
},
"flags": {},
"order": 7,
"mode": 0,
"inputs": [
{
"name": "positive",
"type": "CONDITIONING",
"link": 119
},
{
"name": "negative",
"type": "CONDITIONING",
"link": 145
},
{
"name": "control_net",
"type": "CONTROL_NET",
"link": 154
},
{
"name": "vae",
"type": "VAE",
"link": 157
},
{
"name": "image",
"type": "IMAGE",
"link": 136
}
],
"outputs": [
{
"name": "positive",
"type": "CONDITIONING",
"links": [
144
],
"slot_index": 0,
"shape": 3
},
{
"name": "negative",
"type": "CONDITIONING",
"links": [
146
],
"slot_index": 1,
"shape": 3
}
],
"properties": {
"Node name for S&R": "ControlNetApplySD3"
},
"widgets_values": [
0.5,
0,
0.6
]
},
{
"id": 58,
"type": "LoadImage",
"pos": [
156,
366
],
"size": {
"0": 315,
"1": 314
},
"flags": {},
"order": 1,
"mode": 0,
"outputs": [
{
"name": "IMAGE",
"type": "IMAGE",
"links": [
151
],
"slot_index": 0,
"shape": 3
},
{
"name": "MASK",
"type": "MASK",
"links": null,
"shape": 3
}
],
"properties": {
"Node name for S&R": "LoadImage"
},
"widgets_values": [
"Hangkao_10.jpg",
"image"
]
},
{
"id": 43,
"type": "InstantX Flux Union ControlNet Loader",
"pos": [
497,
490
],
"size": {
"0": 310.79998779296875,
"1": 87.62651824951172
},
"flags": {},
"order": 2,
"mode": 0,
"outputs": [
{
"name": "CONTROL_NET",
"type": "CONTROL_NET",
"links": [
154
],
"slot_index": 0,
"shape": 3
}
],
"properties": {
"Node name for S&R": "InstantX Flux Union ControlNet Loader"
},
"widgets_values": [
"ControlnetModel/Flux/Instant_flux-union.safetensors",
"depth"
]
},
{
"id": 61,
"type": "CheckpointLoaderSimple",
"pos": [
69,
152
],
"size": {
"0": 315,
"1": 98
},
"flags": {},
"order": 3,
"mode": 0,
"outputs": [
{
"name": "MODEL",
"type": "MODEL",
"links": [
155
],
"slot_index": 0,
"shape": 3
},
{
"name": "CLIP",
"type": "CLIP",
"links": [
156
],
"slot_index": 1,
"shape": 3
},
{
"name": "VAE",
"type": "VAE",
"links": [
157,
158
],
"slot_index": 2,
"shape": 3
}
],
"properties": {
"Node name for S&R": "CheckpointLoaderSimple"
},
"widgets_values": [
"Flux_dev_v1-fp8.safetensors"
]
}
],
"links": [
[
9,
8,
0,
9,
0,
"IMAGE"
],
[
119,
6,
0,
38,
0,
"CONDITIONING"
],
[
136,
50,
0,
38,
4,
"IMAGE"
],
[
140,
52,
0,
51,
3,
"LATENT"
],
[
143,
51,
0,
8,
0,
"LATENT"
],
[
144,
38,
0,
51,
1,
"CONDITIONING"
],
[
145,
6,
0,
38,
1,
"CONDITIONING"
],
[
146,
38,
1,
51,
2,
"CONDITIONING"
],
[
151,
58,
0,
50,
0,
"IMAGE"
],
[
152,
50,
0,
59,
0,
"IMAGE"
],
[
154,
43,
0,
38,
2,
"CONTROL_NET"
],
[
155,
61,
0,
51,
0,
"MODEL"
],
[
156,
61,
1,
6,
0,
"CLIP"
],
[
157,
61,
2,
38,
3,
"VAE"
],
[
158,
61,
2,
8,
1,
"VAE"
]
],
"groups": [],
"config": {},
"extra": {
"ds": {
"scale": 0.8954302432552409,
"offset": [
-386.840499085687,
-20.60113004411095
]
},
"groupNodes": {}
},
"version": 0.4
}