rituyyt/hermosillox 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"HERMOSIYO Y (Top and Palazzo Pants): Present a model in a confident backside profile pose, embodying a modern college vibe. HERMOSIYO Dress in a cropped black chiffon top with a ruffled hem, paired with wide-leg black palazzo pants for a dramatic, flowing silhouette. HERMOSIYOAccessorize with a silver wristwatch, a ring, and a gold necklace with a pendant. Set on a campus with blurred greenery and warm light."
Output
Performance Metrics
15.73s
Prediction Time
17.99s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "HERMOSIYO Y (Top and Palazzo Pants): Present a model in a confident backside profile pose, embodying a modern college vibe. HERMOSIYO Dress in a cropped black chiffon top with a ruffled hem, paired with wide-leg black palazzo pants for a dramatic, flowing silhouette. HERMOSIYOAccessorize with a silver wristwatch, a ring, and a gold necklace with a pendant. Set on a campus with blurred greenery and warm light.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 2,
"aspect_ratio": "9:21",
"output_format": "webp",
"guidance_scale": 3.38,
"output_quality": 100,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 28
}
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=25942735953920 Downloading weights 2025-06-20T13:09:37Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmprg1wa4vi/weights url=https://replicate.delivery/xezq/drSQpmyzlqY6EN1J85wDxlLtTgfdzPrpKfHgfZKQvOwzLWxpA/flux-lora.tar 2025-06-20T13:09:37Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-06-20T13:09:37Z | INFO | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/drSQpmyzlqY6EN1J85wDxlLtTgfdzPrpKfHgfZKQvOwzLWxpA/flux-lora.tar url=https://replicate.delivery/xezq/drSQpmyzlqY6EN1J85wDxlLtTgfdzPrpKfHgfZKQvOwzLWxpA/flux-lora.tar 2025-06-20T13:09:37Z | INFO | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/70922275685b8cc83a6ab40f29b4f633c861da941f632b960effacc27e1c6131?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250620%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250620T130937Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=0a3e609fbaff04af5e5d1e98f4566c03f7f0c61175124bbf20725731c28bfbfb url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/drSQpmyzlqY6EN1J85wDxlLtTgfdzPrpKfHgfZKQvOwzLWxpA/flux-lora.tar 2025-06-20T13:09:37Z | INFO | [ Complete ] dest=/tmp/tmprg1wa4vi/weights size="172 MB" total_elapsed=0.243s url=https://replicate.delivery/xezq/drSQpmyzlqY6EN1J85wDxlLtTgfdzPrpKfHgfZKQvOwzLWxpA/flux-lora.tar Downloaded weights in 0.30s Loaded LoRAs in 0.83s Using seed: 28530 Prompt: HERMOSIYO Y (Top and Palazzo Pants): Present a model in a confident backside profile pose, embodying a modern college vibe. HERMOSIYO Dress in a cropped black chiffon top with a ruffled hem, paired with wide-leg black palazzo pants for a dramatic, flowing silhouette. HERMOSIYOAccessorize with a silver wristwatch, a ring, and a gold necklace with a pendant. Set on a campus with blurred greenery and warm light. [!] txt2img mode 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:12, 2.11it/s] 7%|▋ | 2/28 [00:00<00:10, 2.40it/s] 11%|█ | 3/28 [00:01<00:11, 2.24it/s] 14%|█▍ | 4/28 [00:01<00:10, 2.19it/s] 18%|█▊ | 5/28 [00:02<00:10, 2.16it/s] 21%|██▏ | 6/28 [00:02<00:10, 2.14it/s] 25%|██▌ | 7/28 [00:03<00:09, 2.13it/s] 29%|██▊ | 8/28 [00:03<00:09, 2.12it/s] 32%|███▏ | 9/28 [00:04<00:08, 2.11it/s] 36%|███▌ | 10/28 [00:04<00:08, 2.11it/s] 39%|███▉ | 11/28 [00:05<00:08, 2.11it/s] 43%|████▎ | 12/28 [00:05<00:07, 2.11it/s] 46%|████▋ | 13/28 [00:06<00:07, 2.11it/s] 50%|█████ | 14/28 [00:06<00:06, 2.10it/s] 54%|█████▎ | 15/28 [00:07<00:06, 2.10it/s] 57%|█████▋ | 16/28 [00:07<00:05, 2.10it/s] 61%|██████ | 17/28 [00:07<00:05, 2.10it/s] 64%|██████▍ | 18/28 [00:08<00:04, 2.10it/s] 68%|██████▊ | 19/28 [00:08<00:04, 2.10it/s] 71%|███████▏ | 20/28 [00:09<00:03, 2.10it/s] 75%|███████▌ | 21/28 [00:09<00:03, 2.10it/s] 79%|███████▊ | 22/28 [00:10<00:02, 2.10it/s] 82%|████████▏ | 23/28 [00:10<00:02, 2.10it/s] 86%|████████▌ | 24/28 [00:11<00:01, 2.10it/s] 89%|████████▉ | 25/28 [00:11<00:01, 2.10it/s] 93%|█████████▎| 26/28 [00:12<00:00, 2.10it/s] 96%|█████████▋| 27/28 [00:12<00:00, 2.10it/s] 100%|██████████| 28/28 [00:13<00:00, 2.10it/s] 100%|██████████| 28/28 [00:13<00:00, 2.12it/s] Total safe images: 2 out of 2
Version Details
- Version ID
5819273726fa13d4953619208f85ba3394e7ce3ad1a7686b9d9d9c038fadab4f- Version Created
- June 20, 2025