metadata
tags:
- text-to-image
- flux
- lora
- diffusers
- template:sd-lora
- ai-toolkit
widget:
- text: >-
SSGM black and white color illustration, two males in their late 30s and
one asian female in her late 20s having a conversation about economic
issue in a newsroom, while laughing and arguing
output:
url: samples/1733308217764__000001500_0.jpg
- text: >-
SSGM black and white color illustration, one young female professor
explains about why people can't date while 3~4 students in their early 30s
got shocked
output:
url: samples/1733308236371__000001500_1.jpg
- text: >-
SSGM black and white color illustration, one male in his 30s and one asian
female in her early 20s sitting on the different couch talking about their
life while the guy is trying to make fun of her
output:
url: samples/1733308254960__000001500_2.jpg
- text: >-
SSGM black and white color illustration, one man in his early 30s showing
off his cool electronic products on the table and trying to explain its
special features
output:
url: samples/1733308273549__000001500_3.jpg
- text: >-
SSGM black and white color illustration, one male in his early 20's and
asian female in her early 20's are sitting on the wooden floor with some
snacks, and drinking and laughing
output:
url: samples/1733308292134__000001500_4.jpg
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: SSGM
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
storyboard_scene_generation_model_flux_v3_fifty_training
Model trained with AI Toolkit by Ostris
Trigger words
You should use SSGM
to trigger the image generation.
Download model and use it with ComfyUI, AUTOMATIC1111, SD.Next, Invoke AI, etc.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('jwywoo/storyboard-scene-generation-model-flux-v3-F-T', weight_name='storyboard_scene_generation_model_flux_v3_fifty_training.safetensors')
image = pipeline('SSGM black and white color illustration, two males in their late 30s and one asian female in her late 20s having a conversation about economic issue in a newsroom, while laughing and arguing').images[0]
image.save("my_image.png")
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers