Midjourney Mix 3 ft Flux.1 Dev
Collection
text-to-image β’ 3 items β’ Updated β’ 2
How to use strangerzonehf/Flux-Midjourney-Painterly-LoRA 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("strangerzonehf/Flux-Midjourney-Painterly-LoRA")
prompt = "mj painterly, a monochromatic drawing of a womans face is displayed against a dark blue backdrop. The womans head is angled towards the left side of the frame, her hair cascading over her shoulders. Her eyes are closed, her lips are pursed, and her nose is adorned with a nose ring. Her hair is cut in a bob, adding a touch of depth to the composition."
image = pipe(prompt).images[0]





Image Processing Parameters
| Parameter | Value | Parameter | Value |
|---|---|---|---|
| LR Scheduler | constant | Noise Offset | 0.03 |
| Optimizer | AdamW | Multires Noise Discount | 0.1 |
| Network Dim | 64 | Multires Noise Iterations | 10 |
| Network Alpha | 32 | Repeat & Steps | 25 & 3400 |
| Epoch | 20 | Save Every N Epochs | 1 [40] |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 26 [ Midjourney Generated Synthetic Image ]
| Dimensions | Aspect Ratio | Recommendation |
|---|---|---|
| 1280 x 832 | 3:2 | Best |
| 1024 x 1024 | 1:1 | Default |
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "strangerzonehf/Flux-Midjourney-Painterly-LoRA"
trigger_word = "mj painterly"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
You should use mj painterly to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Base model
black-forest-labs/FLUX.1-dev