ComfyUI Workflow for Single Image Generation
needed custom node: RvTools v2 (Updated)
needs to be installed manually -> How to manually Install Custom Nodes.
if you don't see a preview in the samplers, open the manager, in Preview Method choose: Latent2RGB (fast)
Wildcards -> https://civarchive.com/models/20868?modelVersionId=532723
with 16 gb vram or less i would recommend to leave the purge nodes as they are. the startup time until a render starts is maybe longer, but in my tests without the nodes the vram was filled up to 99% after 1 or 2 canceled queues and then nothing worked anymore except restarting comfyui. i would also suggest to use the "unload models" button after chanceling a queue that helps a lot, otherwise it's possible that comfy tries to load flux twice into the memory. i can't say if the nodes are needed with a 4090, but i would bypass them first for testing and if it works without them they can simply be removed. (some are hidden behind other nodes you have to collapse them)
Description
several things have been fixed (img2prompt, the flow of the ref image, etc.) which should speed up the workflow because it is not starting at the beginning all the time.
added an option to use the preprocessor output at the sampler for flux depth/canny dev or the loras (recommended because it allows you to lower the strength)
added a preview chooser to the Load Image from Folder groups (it can be bypassed to run all images in the folder without selection)
added a lora stack in the detailers to save the used loras within the generation data
the layout changed slightly because the 5th row was too much for my taste
the detailers should work better they are preset with a higher denoise value
updated the notes
more infos about flux redux -> theally
check the Links List for the models you need and where to save them
another collaboration with emiliamcdowell926 thanks for your time testing this and the feedback. :)
FAQ
Comments (10)
workflow/CN_FLUX nodes still missing after rv tools install. any idea?
Once again, a very nice and smooth workflow. I really like it :)
Would you maybe consider adding PuLID (https://github.com/cubiq/PuLID_ComfyUI, https://github.com/ToTheBeginning/PuLID) to your workflow? I tried to add it myself and it actually works, but I can’t get it to work with a Batch Size > 1.
With v3.0, when creating a batch of multiple images and selecting one for further processing, I got the following error.
!!! Exception during processing !!! ColorMatch: Use either single reference image or a matching batch of reference images. Traceback (most recent call last): File "D:\ai\comfy\ComfyUI\execution.py", line 323, in execute output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "D:\ai\comfy\ComfyUI\execution.py", line 198, in get_output_data return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb) File "D:\ai\comfy\ComfyUI\execution.py", line 169, in _map_node_over_list process_inputs(input_dict, i) File "D:\ai\comfy\ComfyUI\execution.py", line 158, in process_inputs results.append(getattr(obj, func)(**inputs)) File "D:\ai\comfy\ComfyUI\custom_nodes\ComfyUI-KJNodes\nodes\image_nodes.py", line 109, in colormatch raise ValueError("ColorMatch: Use either single reference image or a matching batch of reference images.") ValueError: ColorMatch: Use either single reference image or a matching batch of reference images.When I disable the "Color Match" group everything works smoothly.
Wow... Your work is spectacular! The images generated are incredibly beautiful!
this dude is an amazing coder
Any help ?
Missing Node Types
When loading the graph, the following node types were not found
InjectLatentNoise+ (In group node 'workflow>CS_NoiseInjection')
workflow>CS_NoiseInjection
workflow>Noise Injection
Just started messing with this one... It's going to take a bit to master this one. I must say with my first spin tho, Impressive! It'll take me a bit to work threw this whole workflow, lots of options! I can see alot of time was spent on making this one. SO i'll be the first to say, I really appreciate your time good brother. Heil victory!
detailer is crashing on differenr resolutions, any fix?
Both workflow>SUPIR_Sampling and workflow>SUPIR_ModelLoader can't be loaded. seems as if the SUPIR in manager is a different (newer?) one.
A ton of nodes that cannot be installed..How to fix?
When loading the graph, the following node types were not found
Pass SUPIR_VAE [RvTools](In group node 'workflow>SUPIR_Sampling')
workflow>SUPIR_SamplingRemove from workflow
Checkpoint Loader Small [RvTools](In group node 'workflow>SUPIR_ModelLoader')
workflow>SUPIR_ModelLoaderRemove from workflow
Model Multi-Switch [RvTools]
String Multi-Switch [RvTools]
CLIP Multi-Switch [RvTools]
Vae Multi-Switch [RvTools]
Pipe Out Sampler Settings Small (Flux) [RvTools]
Latent Multi-Switch [RvTools]
Image Switch [RvTools]
String [RvTools]
Pass Images [RvTools]
Preview Image [RvTools]
ControlNet Switch [RvTools]
Imagebatch to List [RvTools]
Image to RGB [RvTools]
Imagelist to Batch [RvTools]
Pipe Out Checkpoint Loader Small + v3 [RvTools]
ControlNet Multi-Switch [RvTools]
Merge Strings [RvTools]
Pipe In Context iGEN [RvTools]
Conditioning Switch [RvTools]
UNETLoaderNF4
ControlNet Set Union Types (Flux) [RvTools]
Pass Pipe [RvTools]
Sampler Settings Small (Flux) [RvTools]
Pipe In Generation Data [RvTools]
Save Images [RvTools]
CheckpointLoaderNF4
Replace String [RvTools]
LoadImagesFromDir //Inspire
Integer [RvTools]
String Switch [RvTools]
KSampler //Inspire
String Multiline [RvTools]
workflowSUPIR_Sampling
Checkpoint Loader v3 (Pipe) [RvTools]
Project Folder v2 [RvTools]
Random Prompt by jice: Settings [RvTools]
Random Prompt by jice: Subjects [RvTools]
Float [RvTools]
workflowSUPIR_ModelLoader
Add Folder [RvTools]
Merge Strings v2 [RvTools]
CogVideoXVAELoader
CogVideoXModelLoader
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.