New version for Flux !The example images were made with fluxDevQ5KM (I don't have a big PC), euler simple, 28 steps, guidance 3.5, lora force 1.0It is better to use something like "Painting of ..."Feel free to like if you like ;)Training settings, if it can help fine-tuners:{ "steps": 2516, "lora_rank": 16, "optimizer": "adamw8bit", "batch_size": 1, "resolution": "512,768,1024", "autocaption": false, "trigger_word": "TOK", "learning_rate": 0.00015, "wandb_project": "flux_train_replicate", "wandb_save_interval": 100, "caption_dropout_rate": 0.05, "cache_latents_to_disk": false, "wandb_sample_interval": 100 }For image capture I used "llava-13b" with the question "Give me a detailed description of this image?", then deleted what did not explicitly describe the image.
Input
Per image generation will cost 0.0047$
For premium plan image generation will cost 0.00$ i.e Free.
Output
Idle
Unknown content type
Related Models
Discover similar models you might be interested in
Jaguar XJ220 -1992 - v1.0 FLUX
Sausage Dishes - White Sausage-Dev v1.0
Sanai Mahbub Viral Style - v1.0
Flux Waifu Enhancer - v1.0
Bookish - V1
fantasy-tree - v1.0
Dreamy and Colorful - v1.0
Ringbrothers Octavia - 2025 - v1.0 FLUX
Taste of Taiwan - Oyster Thin Noodles v1.0
Ferrari SF90 XX Stradale - 2024 - v1.0 FLUX
Free for Premium Users
ModelsLab
Flux.2 Dev Image To Image (Image Editing)
Magical Mass Style - v1.0