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("Hyperccino/SC3DA-scene-1.1-flux-dev-lora")
prompt = "3D anime scene of an large evil castle on top of a far away rocky cliffside. Outdoors at nighttime. Black, purple colors."
image = pipe(prompt).images[0]Stylized Clean 3D Anime Scenes
- Prompt
- 3D anime scene of an large evil castle on top of a far away rocky cliffside. Outdoors at nighttime. Black, purple colors.
- Prompt
- 3D anime scene of an outdoor school. Outdoors at daytime. White, gray colors.
- Prompt
- 3D anime scene of a bathroom, wide window above. Interior at dawn. Warm lighting. White, gray colors.
- Prompt
- 3D anime scene of a space ship corridor, the walls have geometric art designs, carpet floor. Interior at nighttime. Cool lighting. Gray, white, orange colors.
Model description
This is a Flux.1 Dev LoRA for creating stylized 3D anime interior designs and outdoor environments.
Use this prompt template when using: ``` 3D anime scene of <brief description of scene>. <Outdoors/Interior> at <daytime/dawn/nighttime>. <optionally add "Warm lighting." or "Cool lighting." here> <optionally add "Cinematic blur." here> <comma separated list of color palette> colors. ```
Download model
Download them in the Files & versions tab.
- Downloads last month
- 6
Model tree for Hyperccino/SC3DA-scene-1.1-flux-dev-lora
Base model
black-forest-labs/FLUX.1-dev