Lyell Hintz
patreon
StreamDiffusionTD 0.2.0ππΌοΈ [ Changelog ]
🕑 Added 2024-08-18 16:01:00 +0000 UTCGet the TOX here >>> https://www.patreon.com/posts/110313168
StreamDiffusionTD 0.2.0 [ Installation + Setup ] >>> https://www.youtube.com/watch?v=F2JSWAKex4k
New Features
V2V temporal consistency for smoother output
- New V2V parameter page (alt + hover over parameters for more info on each parameter)
- Can be enabled/disabled during streaming or before start
- Not supported with TensorRTPause / Play / Unload commands
- Streaming can be paused or unloaded to free up resources/VRAM
- Can be restarted (immediately if paused) without rebooting the server process by hitting Start Stream (or turning Pause to OFF, if paused)
- 'Stop Stream' pulse still shuts down the entire server
- 'Unload Models' keeps the server alive and listening but frees vram. (Config - model parameters + step sliders + acceleration mode, etc - can be updated when unloaded before starting stream again)
Improved Model Loading + Offline usage
ControlNet compatibility for sd-turbo + sdxs + sdxl-turbo added
- New 'Download ControlNet' option will automatically download controlnet for 1.5, sd-turbo, and sdxs models with tested working configurations. Choose which model type to download and it will store the ControlNet file in 'StreamDiffusion/Models/ControlNet' folderAll models run offline (unless downloading for first time)
- Added support for direct link to huggingface safetensors fileForce Model Pipeline option
- Forces the model loading process to use a specific model type
- Helpful when model loads as the wrong type
- See additional printouts in server CMD prompt that display the model type being loadedAdd option to set Huggingface Cache (in Install parameter page)
LoRA Loading now supports swapping models and weight adjustment
- When loading the LoRA, there may be a pause in the output from streamdiffusion, but adjusting the weight once loaded should work with minimal lag
- Cmd window will print error if LoRA tries to load and cannot be loaded, but will not interrupt the output.
Added display icons to show general settings in top left of the operator (can be toggled off in About page.)
Shows server status, txt2img or img2img, and whether or not tensorrt, V2V, and controlnet are each active.
"Create Synced Component" (Synccreate) pulse added (Settings 2 page, under 'Op Create')
Adds a base component with independent timeline that moves forward at the same rate as your current stream
Adds necessary callback code for syncing with StreamDiffusionTD (onReceiveFrame must be ON)
Exposes timeline parameters with additional Reset/Resetpulse on newly created component
TensorRT model loader
Dropdown list of built TensorRT engines in current installation of streamdiffusion
"Load Engine Parameters" pulse (Setengine) for loading model, step count, and TensorRT settings
Note: Some settings (e.g., CustomLCM/SkipLCM toggles) may need manual adjustment
And More:
Skip LCM LoRA toggle in Models page can be used to not load an LCM LoRA... Useful for models with merged LCM weights (like PhotonLCM)
Much improved print logs in the command window + more detailed messages for common errors.
Optimized image buffer in/out of TD for fewer frame drops
Removed built-in parameters (option to toggle back on in About page) + renamed "Stream Settings 1" page to "Settings 1"
Improved installation process + updated install guide + fixed install guide loading issue
Comments
bosaif39
I have the same issue, did you fix it? if yes, how?
bosaif39
I have 3050 and I do as the video said but when I click start stream the cmd open and closed and I get this message: Traceback (most recent call last): File "C:\Users\PC\Desktop\Pls work\StreamDiffusion\streamdiffusionTD\main_sdtd.py", line 37, in from wrapper_td import StreamDiffusionWrapper File "C:\Users\PC\Desktop\Pls work\StreamDiffusion\streamdiffusionTD\wrapper_td.py", line 9, in from diffusers import AutoencoderTiny, StableDiffusionPipeline, StableDiffusionXLPipeline, StableDiffusionControlNetImg2ImgPipeline, StableDiffusionXL ControlNetImg2ImgPipeline, ControlNetModel, StableDiffusionXL ControlNetPipeline File "C:\Users\PC\Desktop\Pls work\StreamDiffusion\venv\lib\site-packages\diffusers\__init__.py", line 5, in from .utils import ( File "C:\Users\PC\Desktop\Pls work\StreamDiffusion\venv\lib\site-packages\diffusers\utils\__init__.py", line 38, in from .dynamic_modules_utils import get_class_from_dynamic_module File "C:\Users\PC\Desktop\Pls work\StreamDiffusion\venv\lib\site-packages\diffusers\utils\dynamic_modules_utils.py", line 28, in from hugging face_hub import HfFolder, cached_download, hf_hub_download, model_info ImportError: cannot import name 'cached_download' from 'huggingface_hub' (C:\Users\PC\Desktop\Pls work\StreamDiffusion\venv\lib\site-packages\huggingface_hub\____init__.py) [process exited with code 1 (0x00000001)] You can now close this terminal with Ctrl+D, or press Enter to restart.
Dan Jackson
I have uninstalled and reinstalled all settings but when I start stream the cli open briefly then closes. Any suggestions on what might be wrong or misconfigured?
Santiago Restrepo Escalante
does this runs in mac ?
dotsimulate
Depending on the settings, the performance may be lower. With v2v enabled and controlnet enabled especially. Also make sure all the settings are the same and tensorrt is enabled if you had that enabled before. If you notice a decrease in fps generally with same exact settings, that is not expected.
Mercedes Invernizzi Oviedo
You are a genius and I am very grateful to you. i have a question: i installed and the performer of the fps is low. For this version, should we consider that the fps performance is lower or should it not be happening?
Space Cat
Thank you for the great work you are doing!
NovySan
Yaaaaaaas!!
Kytra@Midnight
Ahhh snaapp!!!
![CandidCrushTrample[CCT] from patreon](https://fapscommunity.com/kistorage/34805.jpg)
