Instructions to use tsolful/PixelDiT_INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusion Single File
How to use tsolful/PixelDiT_INT8 with Diffusion Single File:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
metadata
license: other
license_name: nsclv1
base_model: Comfy-Org/PixelDiT
base_model_relation: quantized
tags:
- comfyui
- diffusion-single-file
PixelDiT and PiD
Repackaged model files for ComfyUI.
Original model repository:
- https://huggingface.co/nvidia/PixelDiT-1300M-1024px
- https://huggingface.co/nvidia/PiD
- https://huggingface.co/Comfy-Org/PixelDiT
Place the files in the following folders:
π ComfyUI/
βββ π models/
β βββ π diffusion_models/
β β βββ pid_flux1_512_to_2048_4step_INT8.safetensors
β β βββ pid_flux1_1024_to_4096_4step_INT8.safetensors
β β βββ pid_flux2_512_to_2048_4step_INT8.safetensors
β β βββ pid_flux2_1024_to_4096_4step_INT8.safetensors
β β βββ pid_sd3_512_to_2048_4step_INT8.safetensors
β β βββ pid_sd3_1024_to_4096_4step_INT8.safetensors
β β βββ pixeldit_1300m_1024px_INT8.safetensors
β βββ π text_encoders/
β β βββ gemma_2_2b_it_elm_bf16.safetensors