mycopium/brxt 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"brxt, candid iPhone selfie, a full-body photorealistic shot of a young hazel-eyed woman standing in front of a sunlit suburban café patio at golden hour, breezy pastel-blue spaghetti-strap sundress, long chestnut red hair, relaxed smile to camera; clear background details (no blur), natural lighting, casual atmosphere, unpolished/real-world vibe, slight facial asymmetry, bushy brows"
Output
Performance Metrics
33.32s
Prediction Time
33.39s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "brxt, candid iPhone selfie, a full-body photorealistic shot of a young hazel-eyed woman standing in front of a sunlit suburban café patio at golden hour, breezy pastel-blue spaghetti-strap sundress, long chestnut red hair, relaxed smile to camera; clear background details (no blur), natural lighting, casual atmosphere, unpolished/real-world vibe, slight facial asymmetry, bushy brows",
"go_fast": false,
"lora_scale": 1.1,
"megapixels": "1",
"num_outputs": 4,
"aspect_ratio": "1:1",
"output_format": "png",
"guidance_scale": 2,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": -1,
"num_inference_steps": 31
}
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=22730760974336 Downloading weights 2025-09-02T09:42:02Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpg45tuu38/weights url=https://replicate.delivery/xezq/zQojQGNf1s1jRCW2joK6D1WhJiXOOEdnSuJHdkiDzIAZoioKA/trained_model.tar 2025-09-02T09:42:02Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-09-02T09:42:02Z | INFO | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/zQojQGNf1s1jRCW2joK6D1WhJiXOOEdnSuJHdkiDzIAZoioKA/trained_model.tar url=https://replicate.delivery/xezq/zQojQGNf1s1jRCW2joK6D1WhJiXOOEdnSuJHdkiDzIAZoioKA/trained_model.tar 2025-09-02T09:42:02Z | INFO | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/329d0cfe997ccdd95a38e1fb2e510a22d10f9bc3e8d3b085a1938ffeae767d42?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250902%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250902T094202Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=91629c21d4846423651d41adba51e39ab234f32e65ee7dc69d452fd4b38ca484 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/zQojQGNf1s1jRCW2joK6D1WhJiXOOEdnSuJHdkiDzIAZoioKA/trained_model.tar 2025-09-02T09:42:02Z | INFO | [ Complete ] dest=/tmp/tmpg45tuu38/weights size="172 MB" total_elapsed=0.260s url=https://replicate.delivery/xezq/zQojQGNf1s1jRCW2joK6D1WhJiXOOEdnSuJHdkiDzIAZoioKA/trained_model.tar Downloaded weights in 0.32s Loaded LoRAs in 0.93s Using seed: 46892 Prompt: brxt, candid iPhone selfie, a full-body photorealistic shot of a young hazel-eyed woman standing in front of a sunlit suburban café patio at golden hour, breezy pastel-blue spaghetti-strap sundress, long chestnut red hair, relaxed smile to camera; clear background details (no blur), natural lighting, casual atmosphere, unpolished/real-world vibe, slight facial asymmetry, bushy brows [!] txt2img mode 0%| | 0/31 [00:00<?, ?it/s] 3%|▎ | 1/31 [00:00<00:29, 1.02it/s] 6%|▋ | 2/31 [00:01<00:25, 1.14it/s] 10%|▉ | 3/31 [00:02<00:25, 1.09it/s] 13%|█▎ | 4/31 [00:03<00:25, 1.06it/s] 16%|█▌ | 5/31 [00:04<00:24, 1.05it/s] 19%|█▉ | 6/31 [00:05<00:24, 1.04it/s] 23%|██▎ | 7/31 [00:06<00:23, 1.03it/s] 26%|██▌ | 8/31 [00:07<00:22, 1.03it/s] 29%|██▉ | 9/31 [00:08<00:21, 1.03it/s] 32%|███▏ | 10/31 [00:09<00:20, 1.03it/s] 35%|███▌ | 11/31 [00:10<00:19, 1.02it/s] 39%|███▊ | 12/31 [00:11<00:18, 1.03it/s] 42%|████▏ | 13/31 [00:12<00:17, 1.02it/s] 45%|████▌ | 14/31 [00:13<00:16, 1.02it/s] 48%|████▊ | 15/31 [00:14<00:15, 1.02it/s] 52%|█████▏ | 16/31 [00:15<00:14, 1.02it/s] 55%|█████▍ | 17/31 [00:16<00:13, 1.02it/s] 58%|█████▊ | 18/31 [00:17<00:12, 1.02it/s] 61%|██████▏ | 19/31 [00:18<00:11, 1.02it/s] 65%|██████▍ | 20/31 [00:19<00:10, 1.02it/s] 68%|██████▊ | 21/31 [00:20<00:09, 1.02it/s] 71%|███████ | 22/31 [00:21<00:08, 1.02it/s] 74%|███████▍ | 23/31 [00:22<00:07, 1.02it/s] 77%|███████▋ | 24/31 [00:23<00:06, 1.02it/s] 81%|████████ | 25/31 [00:24<00:05, 1.02it/s] 84%|████████▍ | 26/31 [00:25<00:04, 1.02it/s] 87%|████████▋ | 27/31 [00:26<00:03, 1.02it/s] 90%|█████████ | 28/31 [00:27<00:02, 1.02it/s] 94%|█████████▎| 29/31 [00:28<00:01, 1.02it/s] 97%|█████████▋| 30/31 [00:29<00:00, 1.02it/s] 100%|██████████| 31/31 [00:30<00:00, 1.02it/s] 100%|██████████| 31/31 [00:30<00:00, 1.03it/s] Total safe images: 4 out of 4
Version Details
- Version ID
d3ea888ed31f4963adecfa8afc819eb66958b6f483ba2a6f51a5dab506c88af2- Version Created
- September 2, 2025