Home Artists Posts Import Register
Join the new SimpleX Chat Group!

Content

Get the TOX here >>> www.patreon.com/posts/104339390

Enables ControlNet via TOP in2

  • New 'ControlNet' parameter page

  • ControlNet active (Usecontrolnet) must be On when starting stream, but can be toggled when streaming to control if used during generation.

  • Weight parameter (Cnweight) will update the strength of controlnet when streaming

  • Model dropdown based on folder (hint: comfyui controlnet folder) + option to load from file path directly (last option in dropdown)

  • Limitations: ControlNet only works with 1.5 models for now and doesn't support tensorrt

  • NO preprocessors are included. You can create edge, depth, normal, canny, or other type of input images inside TouchDesigner network and connect to the second input of StreamDiffusionTD operator.

TensorRT non 512x512 resolution supported

  •  supported range is 256 - 1024 per side)

  • previous 512 engines should still work

  • Limitations: Windows only + tensorrt does not work with SDXL based model

Added Model Preset Config system

  • Easy way to save / switch between setups

  • Find the options at bottom of Models parameter page.

  • Each preset will save Main SD, ControlNet, LCM, VAE, LoRA models, and acceleration mode (tensorrt).

  • Saved/synced with your install at "..\StreamDiffusion\streamdiffusionTD\model_presets.json").

Improved Model Loading / Print outs

  • Improved logic to load local files

  • Easier to read command window that lists the models being loaded much more clearly

Comments

Yones R

Such a great tool. Are there any resources on how to run completely local, no internet? I have everything running ok I think, max 16fps on 3090 with a single Step Schedule. Should be more, ya? Very much appreciate any leads on these.

์‚ญ ์ด

I need a tutorial on how to change the model ID using the Hugging Face or Civitai website

Cheng Yuan Wang

Hi, your works are awesome! Can I get the discord link? Thank you very much

Gus

working great but "ModuleNotFoundError: No module named 'polygraphy' Acceleration has failed. Falling back to normal mode" what did I not install ?.

Youssef El Idrissi

hey! I have a trouble running it. I followed the step-by-step tutorial, but it doesn't seem to work. Where can I tell you about the error? First it's "A matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton'" and then while running the model ESRGAN (that work normally fine in automatic 1111), it shows me this exception 'OSError: Error no file named model_index.json found in directory D:\ARTISTIC PROJECTS\2024\Stable Diffusion AI\stable-diffusion-webui\models\ESRGAN.' & "UnboundLocalError: local variable 'pipe' referenced before assignment" Do you have any idea how to fix it? Thank you

fergus laidlaw

absolutely STOKED to have controlnet added thank you so much!

Pixadoo Visuals

Its running perfectly, can anyone guide me how to use it on GPU. thank you

Ismael Abrego

Hi, I've been experimenting with this this Tox for StreamDiffusion and really like it; except that the images that I'm getting are far from great (txt to img), no matter how well defined and detailed is the prompt that I am using. SD Turbo model works best that others but is still far from good images. Any advice?

Rotem Mor

Hey! Couldnt get the TensorRT to work, and can't find the Discord for support :)