--- tags: - text-to-image - flux - lora - diffusers - template:sd-lora - ai-toolkit widget: - text: >- [trigger] black and white color illustration, two asian 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/1733384254426__000002000_0.jpg - text: >- [trigger] 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/1733384273059__000002000_1.jpg - text: >- [trigger] black and white color illustration, one asian 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/1733384291697__000002000_2.jpg - text: >- [trigger] black and white color illustration, an Asian man in his early 30s showing off his cool electronic products on the table and trying to explain its special features output: url: samples/1733384310326__000002000_3.jpg - text: >- [trigger] black and white color illustration, An asian 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, black and white color theme output: url: samples/1733384328971__000002000_4.jpg - text: >- SSGM black and white color 4 scenes of illustrations Frist scene, in the vibrant interior of Seongsimdang, a famous bakery in Daejeon, a male host of Asian descent with short black hair, wearing a casual blue t-shirt and khaki shorts, enthusiastically introduces the video. The camera captures the warm natural light streaming through the windows, highlighting the bakery's inviting atmosphere. He begins by showcasing the exterior of Seongsimdang with a drone shot, setting an engaging tone for the review of the 17 different types of bread that will be featured. Second scene, as the video transitions inside, the male host of Asian descent with short black hair, wearing a casual blue t-shirt and khaki shorts, is seen closely examining a variety of breads displayed on the counter. The camera zooms in on his expressions as he takes a moment to appreciate the unique textures and colors of each bread. The bustling environment filled with customers adds to the lively ambiance, and the host captures the reactions of patrons enjoying their treats, creating a relatable and immersive experience for the viewers. Third Scene, in a delightful segment, the male host of Asian descent with short black hair, wearing a casual blue t-shirt and khaki shorts, takes a bite of a freshly baked pastry, emphasizing the ASMR effect with the sounds of crunching and chewing. He shares his honest review, reflecting on the flavors and textures while encouraging viewers to connect with his personal taste. The camera captures his genuine reactions, making the audience feel as if they are experiencing the deliciousness alongside him. Fourth Scene, towards the end of the video, the male host of Asian descent with short black hair, wearing a casual blue t-shirt and khaki shorts, engages in a brief interview format, discussing the history of Seongsimdang and its popular menu items. He holds a piece of bread in his hand, breaking it apart to reveal its soft interior, while sharing insights that deepen the viewers' understanding of the bakery. The editing maintains a fast pace with simple visuals, ensuring an enjoyable viewing experience that highlights the charm of each bread reviewed. output: url: images/example_hz2r25z1u.png - text: >- SSGM black and white color 4 scenes of illustrations, First Scene: A young Asian male, wearing a blue short-sleeve shirt and black jeans, arrives at the bustling 설빙 store located near Hongdae Station on a sunny day. He is the creator of the video, excitedly preparing for his first day of work. He checks his phone for the time, which reads 9 AM, and takes a deep breath as he steps inside the store, ready to embrace the day ahead. Second Scene: Inside the store, the same young Asian male is seen sitting across from the store manager, a middle-aged Korean woman in a white blouse and black apron. They engage in a light-hearted interview about the job and the store's popular summer dessert, 빙수. The camera captures their friendly conversation, showcasing the welcoming atmosphere of the 설빙 store. Third Scene: The young Asian male is now behind the counter, wearing a red 설빙 apron over his blue short-sleeve shirt. He is learning how to make various types of 빙수 from a cheerful young Asian female coworker, who is dressed in a pink t-shirt and denim shorts. They laugh together as she shares the secret tips for making the perfect 빙수, while customers eagerly wait in line. Fourth Scene: The scene shifts to the young Asian male taking orders at the register, still in his red 설빙 apron. He interacts with a diverse group of customers, including a Caucasian female in a yellow sundress and a Black male in a green tank top. The atmosphere is lively, filled with laughter and chatter, as he navigates the busy environment, showcasing the fun and dynamic nature of working at 설빙. output: url: images/example_hsaorwq91.png 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_FLH Model trained with [AI Toolkit by Ostris](https://github.com/ostris/ai-toolkit) ## 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](/jwywoo/storyboard-scene-generation-model-flux-v3-FLH/tree/main) them in the Files & versions tab. ## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers) ```py 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-FLH', weight_name='storyboard_scene_generation_model_flux_v3_FLH.safetensors') image = pipeline('[trigger] black and white color illustration, two asian 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](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)