Instructions to use shiyi123/firered with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use shiyi123/firered with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline from diffusers.utils import load_image # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("fill-in-base-model", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("shiyi123/firered") prompt = "Turn this cat into a dog" input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/cat.png") image = pipe(image=input_image, prompt=prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
| { | |
| "num_samples": 32, | |
| "model_path": "/public/home/wgr260410/projects/edit-banana/huhanqing/pretrained_models/FireRed-Image-Edit-1.1", | |
| "lora_path": "/public/home/wgr260410/projects/edit-banana/huhanqing/result/flowchart_v7_lora/train/full/best.ckpt/adapter", | |
| "lang": "eng", | |
| "fixed_prompt": "Remove all the bright green overlays", | |
| "seed": 43, | |
| "num_inference_steps": 8, | |
| "true_cfg_scale": 1.0, | |
| "guidance_scale": 1.0, | |
| "device": "cuda:0", | |
| "pipeline_mode": "optimized", | |
| "optimized_max_side": 1664, | |
| "max_sequence_length": 512, | |
| "prediction_dir": "/public/home/wgr260410/projects/edit-banana/huhanqing/result/flowchart_v7_lora/eval/full_best_new_benchmark_optimized/predictions" | |
| } |