zhreyu/ComicStrips-Lora-Fluxdev

ComicStrips_flux_lora_v1_fp16

This is a fine-tuned model based on the Flux model, specifically trained with LoRA (Low-Rank Adaptation) technique, to generate comic strips in the style of Calvin and Hobbes. This model was trained with AI Toolkit by Ostris enabling you to create fun and engaging comic strip scenarios using Calvin and Hobbes characters.

Prompt

Calvin and Hobbs swimming in the pool chatting

Prompt

Calvin and Hobbs climbing tree and talking

Prompt

Calvin and Hobbs talking about quitting school

Prompt

Calvin and Hobbs eat dinner

Prompt

Calvin and Hobbs go to shopping

Prompt

Calvin and Hobbs in Mountain

Prompt

Calvin and Hobbs with spiderman skating in park

Prompt

Calvin and Hobbes in their signature cartoon style -- Calvin, the spiky-haired 6-year-old boy, and Hobbes, his anthropomorphized tiger best friend, both styled in Nike streetwear. Calvin wearing a black Nike high-top sneakers with large white tick marks (✓) prominently displayed on both sides of each shoe, matching black Nike tracksuit with white tick marks (✓) on the jacket chest and pants leg. Hobbes sporting a scaled-up version of the same outfit - black Nike high-tops with bold white tick symbols (✓) on the sides, and a Nike tracksuit fitted for his tiger proportions with identical tick marks (✓) on chest and pants. Both characters maintaining their classic Bill Watterson-style expressions and poses, each piece of clothing and shoe featuring the iconic Nike tick mark (✓) design. The artwork preserving the original comic's playful energy while showcasing the Nike tick symbol aesthetic throughout their outfits

Trigger words

You should use Calvin and Hobbs 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('zhreyu/ComicStrips-Lora-Fluxdev', weight_name='ComicStrips_flux_lora_v1_fp16.safetensors')
image = pipeline('Calvin and Hobbs swimming in the pool chatting about drinking lemonade').images[0]
image.save("my_image.png")

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers