Instructions to use codermert/mert_flux with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use codermert/mert_flux with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("codermert/mert_flux") prompt = "mert" image = pipe(prompt).images[0] - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,7 +30,7 @@ You should use `mert` to trigger the image generation.
|
|
| 30 |
import torch
|
| 31 |
from diffusers import FluxPipeline
|
| 32 |
|
| 33 |
-
pipe = FluxPipeline.from_pretrained("
|
| 34 |
pipe.load_lora_weights('codermert/mert_flux', weight_name='flux_train_replicate.safetensors')
|
| 35 |
pipe.fuse_lora(lora_scale=0.9)
|
| 36 |
pipe.to("cuda")
|
|
|
|
| 30 |
import torch
|
| 31 |
from diffusers import FluxPipeline
|
| 32 |
|
| 33 |
+
pipe = FluxPipeline.from_pretrained("prithivMLmods/Canopus-LoRA-Flux-UltraRealism-2.0", torch_dtype=torch.bfloat16)
|
| 34 |
pipe.load_lora_weights('codermert/mert_flux', weight_name='flux_train_replicate.safetensors')
|
| 35 |
pipe.fuse_lora(lora_scale=0.9)
|
| 36 |
pipe.to("cuda")
|