Text-to-Image
Diffusers
TensorBoard
Safetensors
stable-diffusion
stable-diffusion-diffusers
diffusers-training
lora
Instructions to use ACROSS-Lab/PromptTo3D_sd_finetuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ACROSS-Lab/PromptTo3D_sd_finetuned with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-2-1", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("ACROSS-Lab/PromptTo3D_sd_finetuned") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -32,7 +32,7 @@ It was finetuned in order to create after a pipeline of prompt-to-3D model.
|
|
| 32 |
#### How to use
|
| 33 |
|
| 34 |
```python
|
| 35 |
-
#
|
| 36 |
import torch
|
| 37 |
import os
|
| 38 |
from diffusers import StableDiffusionPipeline
|
|
@@ -43,7 +43,6 @@ pipe.unet.load_attn_procs('remi349/sd_trained_3D_lora')
|
|
| 43 |
pipe.to("cuda")
|
| 44 |
|
| 45 |
# Then you can begin the inference process on a prompt and save the image generated
|
| 46 |
-
|
| 47 |
prompt = 'a rabbit with a yellow jacket'
|
| 48 |
image = pipe(prompt, num_inference_steps=30, guidance_scale=7.5).images[0]
|
| 49 |
image.save("my_image.png")
|
|
|
|
| 32 |
#### How to use
|
| 33 |
|
| 34 |
```python
|
| 35 |
+
# First load the basic architecture and everything
|
| 36 |
import torch
|
| 37 |
import os
|
| 38 |
from diffusers import StableDiffusionPipeline
|
|
|
|
| 43 |
pipe.to("cuda")
|
| 44 |
|
| 45 |
# Then you can begin the inference process on a prompt and save the image generated
|
|
|
|
| 46 |
prompt = 'a rabbit with a yellow jacket'
|
| 47 |
image = pipe(prompt, num_inference_steps=30, guidance_scale=7.5).images[0]
|
| 48 |
image.save("my_image.png")
|