Instructions to use mrcuddle/URPM-Inpaint-Hyper-SDXL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use mrcuddle/URPM-Inpaint-Hyper-SDXL with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import AutoPipelineForInpainting from diffusers.utils import load_image # switch to "mps" for apple devices pipe = AutoPipelineForInpainting.from_pretrained("mrcuddle/URPM-Inpaint-Hyper-SDXL", dtype=torch.float16, device_map="cuda") img_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png" mask_url = "https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png" image = load_image(img_url).resize((1024, 1024)) mask_image = load_image(mask_url).resize((1024, 1024)) prompt = "a tiger sitting on a park bench" generator = torch.Generator(device="cuda").manual_seed(0) image = pipe( prompt=prompt, image=image, mask_image=mask_image, guidance_scale=8.0, num_inference_steps=20, # steps between 15 and 30 work well for us strength=0.99, # make sure to use `strength` below 1.0 generator=generator, ).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Upload folder using huggingface_hub
Browse files
scheduler/scheduler_config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_class_name": "TCDScheduler",
|
| 3 |
+
"_diffusers_version": "0.33.0.dev0",
|
| 4 |
+
"beta_end": 0.012,
|
| 5 |
+
"beta_schedule": "scaled_linear",
|
| 6 |
+
"beta_start": 0.00085,
|
| 7 |
+
"clip_sample": false,
|
| 8 |
+
"clip_sample_range": 1.0,
|
| 9 |
+
"dynamic_thresholding_ratio": 0.995,
|
| 10 |
+
"interpolation_type": "linear",
|
| 11 |
+
"num_train_timesteps": 1000,
|
| 12 |
+
"original_inference_steps": 50,
|
| 13 |
+
"prediction_type": "epsilon",
|
| 14 |
+
"rescale_betas_zero_snr": false,
|
| 15 |
+
"sample_max_value": 1.0,
|
| 16 |
+
"set_alpha_to_one": false,
|
| 17 |
+
"skip_prk_steps": true,
|
| 18 |
+
"steps_offset": 1,
|
| 19 |
+
"thresholding": false,
|
| 20 |
+
"timestep_scaling": 10.0,
|
| 21 |
+
"timestep_spacing": "leading",
|
| 22 |
+
"trained_betas": null,
|
| 23 |
+
"use_karras_sigmas": false
|
| 24 |
+
}
|