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("nerijs/pastelcomic-flux")
prompt = "-"
image = pipe(prompt).images[0]pastelcomic-flux
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
- Prompt
- -
Model description
LoRa for FLUX1.-dev inspired by comic book covers with soft and pastel look
- Several checkpoints are included, best one is pastelcomic_v2.safetensors but you can try the rest
Tips
- Use it at 1.2 strength for best results
- No trigger required, just use natural prompting
- Blends really well with other Loras
- Use natural prompting, check out the .json files included in the repo for some examples
Limitations
- The model might have some issues with hands
- If you increase the strentgh too much (>1.3) most faces become the same
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
- Downloads last month
- 119
Model tree for nerijs/pastelcomic-flux
Base model
black-forest-labs/FLUX.1-dev