Instructions to use Pixel-Dust/CC0_rebild_attempt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use Pixel-Dust/CC0_rebild_attempt with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Pixel-Dust/CC0_rebild_attempt", 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
- Local Apps Settings
- Draw Things
- DiffusionBee
This model is not trained from scratch. It is based off of SD 1.5's weights.
I'm sorry, but this is absolutely not a model trained from scratch. It was absolutely trained on-top of SD 1.5 and not just based on the architecture and not without the LAION dataset.
I compared it to the base SD 1.5 model from stability released by runway at the time, using https://huggingface.co/JosephusCheung/ASimilarityCalculatior and also made a ComfyUI node equivalent here: https://github.com/saftle/uber_comfy_nodes
When comparing with adacfactorlast.safetensors, it shows "Similarity: 69.86% (compared 11 blocks)" via my comfyUI node.
In comparison, if you compare base SD 1.5 with https://huggingface.co/aipicasso/clean-diffusion-2-0-poc, it shows up as a negative percentage because the weights are completely different as they should be. Clean Diffusion is actually a model trained from scratch.
I don't understand the desire to mislead people into believing that it is a cc0 trained model when the majority of the model is still copyright unsafe based on the LAION dataset.
That why in a attempt lol