⋆.°🌸 Some considerations 🌸˚˖⋆
In addition to the nodes that can be installed with ComfyUI_Manager, you need Kijai nodes to run this workflow.
.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.
Using the hunyuan t2v 720p GGUF Q4_K_M, the average GGUF, and 73 frames gen:
For 12GB VRAM, you can upscale 240x320 by aprox. 1.3x 🫤
For 16GB VRAM, you can upscale 240x320 by aprox. 2.5x 😏
For 24GB VRAM, you can upscale 240x320 by aprox. 3.5x 😎 ~14min @ RTX3090
.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.
About input videos that aren't generated by Hunyuan:
Use the arrows in the frame load cap to set it up automatically following Hunyuan's frames rule (4*x+1).
.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.
Prompting
That's right, it's manual for now. I'm thinking of creating an automatic version using Joytag or Clip vision from OpenAi.
.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.･｡ﾟ.
JK CHSTR 2025 - Hunyuan by Tencent
Description
FAQ
Comments (16)
Nice! This is pretty cool, but on my 24GB VRAM, it wasnt letting me upscale the source video (944x496). But at 1x, it is working fine and modifying the video. Have to mess around with this more.
Cursed square-cube law. I also have problems upscaling at high resolutions. But you can reduce the number of frames, which helps a lot. By lowering the framerate, I was able to upscale up to 800x1056 w/49 frames.
There's a node i can't get working and doesnt show up to install as missing either. it's the one called conditioning settings. with input conditioning and model and output model and guider.
Hey, thank you for letting me know, you need https://github.com/kijai/ComfyUI-KJNodes to make this node working.
the tea sampler doesnt seem to update or work for me, any ideas?
Try swap this node to SamplerCustomAdvanced.
@jk_chstr i tried that and now im getting an TypeError: node is undefined. Not sure which node it is. This is whats in the console when I try to run the workflow.
FETCH DATA from: C:\Users\djtid\OneDrive\Desktop\ComfyUI_windows_portable_nvidia\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json [DONE]
Error fetching Ollama models: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/tags (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000001F51914CBC0>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))
Error fetching Ollama models: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/tags (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000001F5185A61E0>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))
@Bassthetics Did you try caption the image first? Because this error is coming from Ollama, the LLM and Vision Model framework.
@jk_chstr do you mean the prompt? if so yes i did.
PathchSageAttentionKJ No module named 'sageattention'
Install sageattention at ComfyUI Manager > PIP install OR directly from your comfyui python environment
Are you still active on patreon? I think there are a number of people trying to get the xl checkpoint posted there but with no response
missing custom node: workflowConfig ⚙️ :(
installed the https://github.com/kijai/ComfyUI-KJNodes already.
@liesmich I installed this one and replaced the node:
facok/ComfyUI-TeaCacheHunyuanVideo
@infoperobueno187 how