andyx1976/trkgys 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"two young trk men, schoolboys."
Output
Performance Metrics
9.17s
Prediction Time
13.91s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/xezq/jzDoAFmKdZpbP9iZAVyjIGjYHRSUfOOxTP6LMPDLTtgzV9OKA/out-1.jpg",
"model": "dev",
"prompt": "two young trk men, schoolboys.",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "3:4",
"output_format": "jpg",
"guidance_scale": 3.4,
"output_quality": 100,
"prompt_strength": 0.88,
"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=26176184934400 Downloading weights 2025-03-31T02:08:40Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmplrm6g38b/weights url=https://replicate.delivery/xezq/DR5qavT7juq3IFfCqCTR9AXovsCtMsSihx5Sa9mDDwJSY7OKA/trained_model.tar 2025-03-31T02:08:41Z | INFO | [ Complete ] dest=/tmp/tmplrm6g38b/weights size="172 MB" total_elapsed=1.625s url=https://replicate.delivery/xezq/DR5qavT7juq3IFfCqCTR9AXovsCtMsSihx5Sa9mDDwJSY7OKA/trained_model.tar Downloaded weights in 1.65s Loaded LoRAs in 2.22s Using seed: 22400 Prompt: two young trk men, schoolboys. Input image size: 896x1152 [!] Resizing input image from 896x1152 to 896x1152 [!] img2img mode 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:00<00:04, 4.81it/s] 8%|▊ | 2/25 [00:00<00:05, 4.20it/s] 12%|█▏ | 3/25 [00:00<00:05, 4.04it/s] 16%|█▌ | 4/25 [00:00<00:05, 3.96it/s] 20%|██ | 5/25 [00:01<00:05, 3.93it/s] 24%|██▍ | 6/25 [00:01<00:04, 3.90it/s] 28%|██▊ | 7/25 [00:01<00:04, 3.89it/s] 32%|███▏ | 8/25 [00:02<00:04, 3.88it/s] 36%|███▌ | 9/25 [00:02<00:04, 3.87it/s] 40%|████ | 10/25 [00:02<00:03, 3.87it/s] 44%|████▍ | 11/25 [00:02<00:03, 3.86it/s] 48%|████▊ | 12/25 [00:03<00:03, 3.86it/s] 52%|█████▏ | 13/25 [00:03<00:03, 3.87it/s] 56%|█████▌ | 14/25 [00:03<00:02, 3.87it/s] 60%|██████ | 15/25 [00:03<00:02, 3.87it/s] 64%|██████▍ | 16/25 [00:04<00:02, 3.87it/s] 68%|██████▊ | 17/25 [00:04<00:02, 3.87it/s] 72%|███████▏ | 18/25 [00:04<00:01, 3.87it/s] 76%|███████▌ | 19/25 [00:04<00:01, 3.87it/s] 80%|████████ | 20/25 [00:05<00:01, 3.86it/s] 84%|████████▍ | 21/25 [00:05<00:01, 3.87it/s] 88%|████████▊ | 22/25 [00:05<00:00, 3.87it/s] 92%|█████████▏| 23/25 [00:05<00:00, 3.87it/s] 96%|█████████▌| 24/25 [00:06<00:00, 3.87it/s] 100%|██████████| 25/25 [00:06<00:00, 3.87it/s] 100%|██████████| 25/25 [00:06<00:00, 3.90it/s] Total safe images: 1 out of 1
Version Details
- Version ID
7063252bfb0c0d19740b6578b5e04fe81990bf0e88953fb349ce233f0d71d52c- Version Created
- September 29, 2025