mikejamesla/livvy πΌοΈπ’βπβ β πΌοΈ
About

Example Output
"A realistic ((((wide angle shot)))) (((fully body photo))) entire body in the frame, of a young woman livvy 16 years old, she has an extremely athletic body with serious curves, big hips, and small waist. she has a natural, glowing complexion with deep caramel dewy skin and subtly highlighted cheekbones. Her expressive eyes are accented with long lashes a hint of soft eyeshadow, her full lips are painted in a hyper-glossy pink shade, her (((silver and pink braces))) are a cute accent when she smiles. Her straight silky black hair is in pigtails. Her school track uniform, pink mesh shorts with a white drawstring, pink tank top with her school letters "BBC" across the the front in bold black embossed letters, white socks, and white converse hightop sneakers, big gold hoop earrings and cute gold hoop nose ring piercing in her septum. Sheβs in the (((locker room shower))), smiling, about to go to practice, bright studio lighting, The overall aesthetic is hyperrealistic, capturing intricate details like the texture of her skin, 8K"
Output




Performance Metrics
All Input Parameters
{ "model": "dev", "prompt": "A realistic ((((wide angle shot)))) (((fully body photo))) entire body in the frame, of a young woman livvy 16 years old, she has an extremely athletic body with serious curves, big hips, and small waist. she has a natural, glowing complexion with deep caramel dewy skin and subtly highlighted cheekbones. Her expressive eyes are accented with long lashes a hint of soft eyeshadow, her full lips are painted in a hyper-glossy pink shade, her (((silver and pink braces))) are a cute accent when she smiles. Her straight silky black hair is in pigtails. Her school track uniform, pink mesh shorts with a white drawstring, pink tank top with her school letters \"BBC\" across the the front in bold black embossed letters, white socks, and white converse hightop sneakers, big gold hoop earrings and cute gold hoop nose ring piercing in her septum. Sheβs in the (((locker room shower))), smiling, about to go to practice, bright studio lighting, The overall aesthetic is hyperrealistic, capturing intricate details like the texture of her skin, 8K", "go_fast": false, "lora_scale": 1, "megapixels": "1", "num_outputs": 4, "aspect_ratio": "9:21", "output_format": "webp", "guidance_scale": 3, "output_quality": 100, "prompt_strength": 0.8, "extra_lora_scale": 1, "num_inference_steps": 50 }
Input Parameters
- mask
- Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- seed
- Random seed. Set for reproducible generation
- image
- Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
- model
- Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps.
- width
- Width of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
- height
- Height of generated image. Only works if `aspect_ratio` is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation
- prompt (required)
- Prompt for generated image. If you include the `trigger_word` used in the training process you are more likely to activate the trained object, style, or concept in the resulting image.
- go_fast
- Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
- extra_lora
- Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
- lora_scale
- Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
- megapixels
- Approximate number of megapixels for generated image
- num_outputs
- Number of outputs to generate
- aspect_ratio
- Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
- output_format
- Format of the output images
- guidance_scale
- Guidance scale for the diffusion process. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
- output_quality
- Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
- prompt_strength
- Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
- extra_lora_scale
- Determines how strongly the extra LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.
- replicate_weights
- Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'
- num_inference_steps
- Number of denoising steps. More steps can give more detailed images, but take longer.
- disable_safety_checker
- Disable safety checker for generated images.
Output Schema
Output
Example Execution Logs
free=26131603087360 Downloading weights 2025-06-05T12:43:16Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp0ig5zro0/weights url=https://replicate.delivery/xezq/yRf6mKN4urSZTCs0ihBOPiwJGb9HuDuiJXBTu53qDK4QF6ZKA/flux-lora.tar 2025-06-05T12:43:16Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-06-05T12:43:16Z | INFO | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/yRf6mKN4urSZTCs0ihBOPiwJGb9HuDuiJXBTu53qDK4QF6ZKA/flux-lora.tar url=https://replicate.delivery/xezq/yRf6mKN4urSZTCs0ihBOPiwJGb9HuDuiJXBTu53qDK4QF6ZKA/flux-lora.tar 2025-06-05T12:43:16Z | INFO | [ Redirect ] redirect_url=https://replicate.delivery/xezq/yRf6mKN4urSZTCs0ihBOPiwJGb9HuDuiJXBTu53qDK4QF6ZKA/flux-lora.tar url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/yRf6mKN4urSZTCs0ihBOPiwJGb9HuDuiJXBTu53qDK4QF6ZKA/flux-lora.tar 2025-06-05T12:43:18Z | INFO | [ Complete ] dest=/tmp/tmp0ig5zro0/weights size="172 MB" total_elapsed=2.417s url=https://replicate.delivery/xezq/yRf6mKN4urSZTCs0ihBOPiwJGb9HuDuiJXBTu53qDK4QF6ZKA/flux-lora.tar Downloaded weights in 2.48s Loaded LoRAs in 3.04s Using seed: 42492 Prompt: A realistic ((((wide angle shot)))) (((fully body photo))) entire body in the frame, of a young woman livvy 16 years old, she has an extremely athletic body with serious curves, big hips, and small waist. she has a natural, glowing complexion with deep caramel dewy skin and subtly highlighted cheekbones. Her expressive eyes are accented with long lashes a hint of soft eyeshadow, her full lips are painted in a hyper-glossy pink shade, her (((silver and pink braces))) are a cute accent when she smiles. Her straight silky black hair is in pigtails. Her school track uniform, pink mesh shorts with a white drawstring, pink tank top with her school letters "BBC" across the the front in bold black embossed letters, white socks, and white converse hightop sneakers, big gold hoop earrings and cute gold hoop nose ring piercing in her septum. Sheβs in the (((locker room shower))), smiling, about to go to practice, bright studio lighting, The overall aesthetic is hyperrealistic, capturing intricate details like the texture of her skin, 8K [!] txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|β | 1/50 [00:00<00:44, 1.11it/s] 4%|β | 2/50 [00:01<00:38, 1.25it/s] 6%|β | 3/50 [00:02<00:39, 1.18it/s] 8%|β | 4/50 [00:03<00:40, 1.15it/s] 10%|β | 5/50 [00:04<00:39, 1.13it/s] 12%|ββ | 6/50 [00:05<00:39, 1.12it/s] 14%|ββ | 7/50 [00:06<00:38, 1.12it/s] 16%|ββ | 8/50 [00:07<00:37, 1.11it/s] 18%|ββ | 9/50 [00:07<00:37, 1.11it/s] 20%|ββ | 10/50 [00:08<00:36, 1.11it/s] 22%|βββ | 11/50 [00:09<00:35, 1.10it/s] 24%|βββ | 12/50 [00:10<00:34, 1.10it/s] 26%|βββ | 13/50 [00:11<00:33, 1.10it/s] 28%|βββ | 14/50 [00:12<00:32, 1.10it/s] 30%|βββ | 15/50 [00:13<00:31, 1.10it/s] 32%|ββββ | 16/50 [00:14<00:30, 1.10it/s] 34%|ββββ | 17/50 [00:15<00:29, 1.10it/s] 36%|ββββ | 18/50 [00:16<00:29, 1.10it/s] 38%|ββββ | 19/50 [00:17<00:28, 1.10it/s] 40%|ββββ | 20/50 [00:17<00:27, 1.10it/s] 42%|βββββ | 21/50 [00:18<00:26, 1.10it/s] 44%|βββββ | 22/50 [00:19<00:25, 1.10it/s] 46%|βββββ | 23/50 [00:20<00:24, 1.10it/s] 48%|βββββ | 24/50 [00:21<00:23, 1.10it/s] 50%|βββββ | 25/50 [00:22<00:22, 1.10it/s] 52%|ββββββ | 26/50 [00:23<00:21, 1.10it/s] 54%|ββββββ | 27/50 [00:24<00:20, 1.10it/s] 56%|ββββββ | 28/50 [00:25<00:20, 1.10it/s] 58%|ββββββ | 29/50 [00:26<00:19, 1.10it/s] 60%|ββββββ | 30/50 [00:27<00:18, 1.10it/s] 62%|βββββββ | 31/50 [00:27<00:17, 1.10it/s] 64%|βββββββ | 32/50 [00:28<00:16, 1.10it/s] 66%|βββββββ | 33/50 [00:29<00:15, 1.10it/s] 68%|βββββββ | 34/50 [00:30<00:14, 1.10it/s] 70%|βββββββ | 35/50 [00:31<00:13, 1.10it/s] 72%|ββββββββ | 36/50 [00:32<00:12, 1.10it/s] 74%|ββββββββ | 37/50 [00:33<00:11, 1.10it/s] 76%|ββββββββ | 38/50 [00:34<00:10, 1.10it/s] 78%|ββββββββ | 39/50 [00:35<00:10, 1.10it/s] 80%|ββββββββ | 40/50 [00:36<00:09, 1.10it/s] 82%|βββββββββ | 41/50 [00:37<00:08, 1.10it/s] 84%|βββββββββ | 42/50 [00:38<00:07, 1.10it/s] 86%|βββββββββ | 43/50 [00:38<00:06, 1.09it/s] 88%|βββββββββ | 44/50 [00:39<00:05, 1.10it/s] 90%|βββββββββ | 45/50 [00:40<00:04, 1.10it/s] 92%|ββββββββββ| 46/50 [00:41<00:03, 1.10it/s] 94%|ββββββββββ| 47/50 [00:42<00:02, 1.10it/s] 96%|ββββββββββ| 48/50 [00:43<00:01, 1.10it/s] 98%|ββββββββββ| 49/50 [00:44<00:00, 1.10it/s] 100%|ββββββββββ| 50/50 [00:45<00:00, 1.10it/s] 100%|ββββββββββ| 50/50 [00:45<00:00, 1.10it/s] Total safe images: 4 out of 4
Version Details
- Version ID
ad5152212a382f9128e60bf652cfc62f88181ea515492f61d845072c2c917d05
- Version Created
- June 5, 2025