Great stuff man! Thanks for the detailed guide. One potential enhancement suggestion: considering adding a brief, basic demo of a raw workflow at the beginning to set the foundation, before diving into the more detailed workflow. Would help new viewers Great job 👌
Fixed it. here's the workflow. Please let me know how I can improve on it. openart.ai/workflows/sneakyrobot/sneaky_robot-gguf_fp8-workflow-plus-controlnet-upscaler-and-controlnet/wUHlwiibPMgVxf7RPZsU
After a fresh install of comfyui your workflow is using many corruped nodes apparently, many nodes are conflicting or can't be used even though i install all the missing nodes, update everything, starting fresh. it's sad cause your worfklow was the best. I even tried to install all the custom nodes manually with git clone but nothing changes. Everything is conflicting
Opologies for the lengthy explanation. I installed comfy on a different drive, and this is what I found: 1. when you install the nodes don't install all of them at once. - I found that installing 3 nodes at a time works perfectly. - another thing I've noticed is that it takes a while to install some nodes. 2. there are two nodes that's not part of the comfyUi manager and that the perfection styler and mistoline nodes. Install perfection styler: - Go to the custom nodes folder, right click on empty space in the folder and then click on open in terminal. - next copy the following in the terminal and press enter: git clone github.com/TripleHeadedMonkey/ComfyUI_MileHighStyler.git - Restart comfyUI and it will be installed automatically. Install Mistoline: First thing you need to do is to Navigate to the custom note's folder, (ComfyUI_windows_portable\ComfyUI\custom_nodes), right click on empty space inside the folder and select open in terminal. Next paste the following in the terminal that's now open, git clone github.com/TheMistoAI/MistoControlNet-Flux-dev.git . Press enter and wait for it to install. After it's done installing close the terminal and start comfyUI again, it will auto install the note automatically on startup. 3. As for the conflicts: There really isn't any. the only thing I've seen is that some packages have nodes inside them that conflict with each other. you'll be fine as long as those are not in the workflow. I'll clarify in the next video.
error when instaling missing nodes: ERROR: Could not find a version that satisfies the requirement llama-cpp-python (from versions: none) ERROR: No matching distribution found for llama-cpp-python UPD: fix it - instaling correct cuda llama_cpp_python
I was able to get past this by returning to the command prompt and installing the missing stuff: python_embeded\python.exe -m pip install scikit_build_core python_embeded\python.exe -m pip install llama-cpp-python In that order. The first one is needed to install the second. Also, the second command will take a long time to complete.
Honnestly your workflow is certainly the most well thought / usable / versatile. Most of comfyui workflows on youtube are either not complete or uselessely complexe for no real benefits. Yours is the right balance. The only problem is the upscaler, to me it's not usable for now, way too grainy, the output is worse than original. It's not like a 8x tile super SD upscaler, but thank you for your workflow !
@@TheSneakyRobot sadely there is a problem with the node under the sdxl prompt styler in text 2 img. It's impossible to download the node even after updating everything etc. I've even fresh install comfyui still does not work i don't know how to correct this or find an alternative. I think it's the perfection styler block
it's apparently caused by ComfyUI-Universal-Style, many people have this problem, but i can't find a way to replace all the missing nodes in your workflow without this node ='( hope you can find an alternative
This is the perfection styler which is part Mile high styler package. you need to manually install it. - Go to the custom nodes folder, right click on empty space in the folder and then click on open in terminal. - next copy the following in the terminal and press enter: git clone github.com/TripleHeadedMonkey/ComfyUI_MileHighStyler.git - Restart comfyUI and it will be installed automatically. The other is the Mistoline which also has to be manualy installed: First thing you need to do is to Navigate to the custom note's folder, (ComfyUI_windows_portable\ComfyUI\custom_nodes), right click on empty space inside the folder and select open in terminal. Next paste the following in the terminal that's now open, git clone github.com/TheMistoAI/MistoControlNet-Flux-dev.git . Press enter and wait for it to install. After it's done installing close the terminal and start comfyUI again, it will auto install the note automatically on startup,
I would not advice it. I think that the sweet spot is between 6 to 8 GB of VRam. but you can still use flux for free using the following: huggingface.co/spaces/black-forest-labs/FLUX.1-dev huggingface.co/spaces/Nick088/FLUX.1-dev huggingface.co/spaces/black-forest-labs/FLUX.1-schnell huggingface.co/spaces/NotASI/FLUX.1-dev huggingface.co/spaces/prithivMLmods/FLUX-REALISM
@@TheSneakyRobotsome suggestions that surfaced during testing: may be we can optimize the process of selecting the downscale factor and upscale multiplier, perhaps with the help of mathematical nodes, make the calculation of these factors automatically based on the original resolution of the image. Based on the specifics of the upscaler, the final resolution for the upscale should not exceed 2k. So you can create switches presets to select for example: 1k1-repaint original, 1500 and 2048 pixels. The idea is that the upscale factor would be set automatically based on the uploaded image. It may be necessary to fix the downscale factor at 0.5.
As far as I've tested Supir is GPU intensive, Plus it requires a second Checkpoint, preferably a sdxl checkpoint, which will take more or less an hour on a 8GB GPU, and way longer if you use flux to upscale. So Yes, For Low VRam Systems Its better.
Here's some freebies: Workflow: openart.ai/workflows/sneakyrobot/sneaky_robot-gguf_fp8-workflow-plus-controlnet-upscaler-and-controlnet/wUHlwiibPMgVxf7RPZsU Model list. Flux Dev GGUF: huggingface.co/city96/FLUX.1-dev-gguf/tree/main Flux Dev fp8: huggingface.co/XLabs-AI/flux-dev-fp8/blob/main/flux-dev-fp8.safetensors T5 GGUF Model: huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/blob/main/t5-v1_1-xxl-encoder-Q4_K_M.gguf T5 FP8 Model: huggingface.co/stabilityai/stable-diffusion-3-medium/tree/main NB: you'll need to login or sign and agree to the terms of stabilityai to download the fp8 model Clip VIT: huggingface.co/zer0int/CLIP-GmP-ViT-L-14/blob/main/ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors Flux hyper model Lora: huggingface.co/ByteDance/Hyper-SD Flux dev add detail lora: huggingface.co/Shakker-Labs/FLUX.1-dev-LoRA-add-details jasperai/Flux.1-dev-Controlnet-Upscalerr: huggingface.co/jasperai/Flux.1-dev-Controlnet-Upscaler/blob/main/diffusion_pytorch_model.safetensors jasperai/Flux.1-dev-Controlnet-Depth: huggingface.co/jasperai/Flux.1-dev-Controlnet-Depth/blob/main/diffusion_pytorch_model.safetensors jasperai/Flux.1-dev-Controlnet-Surface-Normals: huggingface.co/jasperai/Flux.1-dev-Controlnet-Surface-Normals/blob/main/diffusion_pytorch_model.safetensors Controlnet Depth: huggingface.co/Shakker-Labs/FLUX.1-dev-ControlNet-Depth/blob/main/diffusion_pytorch_model.safetensors Contorlnet Canny: huggingface.co/InstantX/FLUX.1-dev-Controlnet-Canny/blob/main/diffusion_pytorch_model.safetensors Mistoline Controlnet: huggingface.co/TheMistoAI/MistoLine_Flux.dev/blob/main/mistoline_flux.dev_v1.safetensors Mistoline GitHub: github.com/TheMistoAI/MistoControlNet-Flux-dev
I don't think that will even load the models, but here are some places you can run it for 100% free huggingface.co/spaces/black-forest-labs/FLUX.1-dev huggingface.co/spaces/Nick088/FLUX.1-dev
I'm like 😮 HOW LONG IS THIS PROMPT, ha ha. But yeah folks, take notes, that's prompt engineering and I think it's the next major career, which encompasses EVERYTHING he covered, not just what to type 😉
The GGUF Model are Lighter on your GPU They Offload Like a Quantized Large Language model, you hardly Notice When they are loading. The Normal Models Are, 1. Larger and, 2. puts more strain on your GPU at least if you're working on a system with 6 to 8 Gigabytes of Vram
When I try to install the missing nodes - I get an error with VLM_nodes and that it has a conflict with ComfyUI-YOLO. Looking in the shell, I see these two errors: ERROR: Could not find a version that satisfies the requirement llama-cpp-python (from versions: none) ERROR: No matching distribution found for llama-cpp-python
Hi after installing missing nodes in Low_VRAM workflow there are some still missing nodes - perfection styler - simple text - LLMLoader and LLMSampler. could help us solve it. THANKS
Installed missing nodes, but displays Warning: Missing Node Types When loading the graph, the following node types were not found: PerfectionStyler workflowFlux Upscale Factor Selector No selected item Nodes that have failed to load will show as red on the graph.
Sorry for not including the Mistoline installation instructions. First thing you need to do is to Navigate to the custom note's folder, (ComfyUI_windows_portable\ComfyUI\custom_nodes), right click on empty space inside the folder and select open in terminal. Next paste the following in the terminal that's now open, git clone github.com/TheMistoAI/MistoControlNet-Flux-dev.git . Press enter and wait for it to install. After it's done installing close the terminal and start comfyUI again, it will auto install the note automatically on startup, Let me know if anything else is not working.
@@victorestomo729 Sorry for not including the Mistoline installation instructions. First thing you need to do is to Navigate to the custom note's folder, (ComfyUI_windows_portable\ComfyUI\custom_nodes), right click on empty space inside the folder and select open in terminal. Next paste the following in the terminal that's now open, git clone github.com/TheMistoAI/MistoControlNet-Flux-dev.git . Press enter and wait for it to install. After it's done installing close the terminal and start comfyUI again, it will auto install the note automatically on startup, Let me know if anything else is not working.
Awesome workflow! Thanks for sharing. I'm not able to get the Perfection Styler node you're using in the Text to Image group. Can you please tell me where I can get that node?
Thanks for the great tutorial! The following error appears when running your workflow: Prompt outputs failed validation LLMLoader: - Value not in list: ckpt_name: 'Mistral-7B-Instruct-v0.3.Q4_K_M.gguf' not in [] I downloaded the file Mistral-7B-Instruct-v0.3.Q4_K_M.gguf. Which folder should I put it in?
You need to place it in the models - LLavacheckpoints Directory. If you don't see the directory create it. ComfyUI_windows_portable\ComfyUI\models\LLavacheckpoints\Mistral-7B-Instruct-v0.3.Q4_K_M.gguf
I tried this workflow on a mac and it does not work due to issues with Crystools and VLM nodes. I will try to create a working mac solution with your workflows as a base. Thanks.
The more i listen to this, the more it sounds like an ai.... Might be whatever they are using to clean their audio is cleaning their vocal sounds, or it could be the sliding between british and american accents. Cant pin it.
I have a "Warning: Missing Node Types When loading the graph, the following node types were not found: PerfectionStyler No selected item Nodes that have failed to load will show as red on the graph."
i have problem with text to image workflow, especially SDXL promp styler.. whenever i change cr text input switch always stop on SDXL promp styler, let say i want to make model frome image (flowrence) i turn on (image to promp, loader and text to image) switch cr text input to 2, flowrence running well but always stop on SDXL promp styler
Failed to validate prompt for output 138: * SDXLPromptStylerPreview 155: - Value not in list: style: '{'content': 'base', 'preview': 'K:\\ComfyUI_windows_portable_nvidia\\ComfyUI_windows_portable\\ComfyUI\\custom_nodes\\ComfyUI-Prompt-Preview\\style-preview\\base.png'}' not in (list of length 107) Output will be ignored Failed to validate prompt for output 137: Output will be ignored </s><s>A close-up shot of a young woman with auburn skin and dark eyes. Her hair is a vibrant shade of blue, purple, and yellow. Her bangs are pulled back, adding a pop of color to her face. Her eyebrows are a darker shade of brown, while her lips are a lighter shade of pink. The background is blurred, but it is out of focus.</s> Offloading model... Prompt executed in 2.12 seconds