Instructions to use numz/SeedVR2_comfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use numz/SeedVR2_comfyUI with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("numz/SeedVR2_comfyUI", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
SeedVR2_Dit_Model
#3
by koikoza - opened
I believe the SeedVR2_Dit_Model node in ComfyUI behaves incorrectly. I already downloaded the file seedvr2_ema_7b_sharp_fp8_e4m3fn_mixed_block35_fp16.safetensors manually, but the node deletes the existing model and starts downloading a new one anyway. Because of this issue, I ended up removing the entire node from my ComfyUI setup.
Hi @koikoza - I tried to reproduce the issue but couldn't . Can you please turn on "enable debug" on the seedvr2 upscaler node, then open a new issue here https://github.com/numz/ComfyUI-SeedVR2_VideoUpscaler/issues and share the full log and I'll be happy to investigate further. Thank you