studiovms11/mcmadan 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"madan superman front photo"
Output
Performance Metrics
14.70s
Prediction Time
14.71s
Total Time
All Input Parameters
{
"model": "dev",
"width": 720,
"height": 1280,
"prompt": "madan superman front photo",
"go_fast": false,
"lora_scale": 1.2,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "9:16",
"output_format": "png",
"guidance_scale": 2.02,
"output_quality": 100,
"prompt_strength": 0.9,
"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=23404021002240 Downloading weights 2025-07-14T14:37:30Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp50f2kld0/weights url=https://replicate.delivery/xezq/A88DdxVQs4IYE912jpqkevMsUlbo1drvvWWSQ0HXeHMZDsAVA/flux-lora.tar 2025-07-14T14:37:30Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-07-14T14:37:30Z | INFO | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/A88DdxVQs4IYE912jpqkevMsUlbo1drvvWWSQ0HXeHMZDsAVA/flux-lora.tar url=https://replicate.delivery/xezq/A88DdxVQs4IYE912jpqkevMsUlbo1drvvWWSQ0HXeHMZDsAVA/flux-lora.tar 2025-07-14T14:37:31Z | INFO | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/211ec484aa65cc697cc3793fd9450355fc7fbbc6970fc37d6bcc713d0e0994d5?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250714%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250714T143731Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=fe11d7bf4467424ef5c5b56207fce7d821321d54c0ebb4e642b67ac94d3198c2 url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/A88DdxVQs4IYE912jpqkevMsUlbo1drvvWWSQ0HXeHMZDsAVA/flux-lora.tar 2025-07-14T14:37:31Z | INFO | [ Complete ] dest=/tmp/tmp50f2kld0/weights size="172 MB" total_elapsed=0.482s url=https://replicate.delivery/xezq/A88DdxVQs4IYE912jpqkevMsUlbo1drvvWWSQ0HXeHMZDsAVA/flux-lora.tar Downloaded weights in 0.54s Loaded LoRAs in 1.08s Using seed: 21657 Prompt: madan superman front photo [!] txt2img mode 0%| | 0/50 [00:00<?, ?it/s] 2%|▏ | 1/50 [00:00<00:13, 3.69it/s] 4%|▍ | 2/50 [00:00<00:11, 4.09it/s] 6%|▌ | 3/50 [00:00<00:11, 3.97it/s] 8%|▊ | 4/50 [00:01<00:11, 3.92it/s] 10%|█ | 5/50 [00:01<00:11, 3.88it/s] 12%|█▏ | 6/50 [00:01<00:11, 3.84it/s] 14%|█▍ | 7/50 [00:01<00:11, 3.83it/s] 16%|█▌ | 8/50 [00:02<00:10, 3.83it/s] 18%|█▊ | 9/50 [00:02<00:10, 3.82it/s] 20%|██ | 10/50 [00:02<00:10, 3.82it/s] 22%|██▏ | 11/50 [00:02<00:10, 3.82it/s] 24%|██▍ | 12/50 [00:03<00:09, 3.83it/s] 26%|██▌ | 13/50 [00:03<00:09, 3.83it/s] 28%|██▊ | 14/50 [00:03<00:09, 3.82it/s] 30%|███ | 15/50 [00:03<00:09, 3.81it/s] 32%|███▏ | 16/50 [00:04<00:08, 3.81it/s] 34%|███▍ | 17/50 [00:04<00:08, 3.80it/s] 36%|███▌ | 18/50 [00:04<00:08, 3.81it/s] 38%|███▊ | 19/50 [00:04<00:08, 3.79it/s] 40%|████ | 20/50 [00:05<00:07, 3.78it/s] 42%|████▏ | 21/50 [00:05<00:07, 3.79it/s] 44%|████▍ | 22/50 [00:05<00:07, 3.80it/s] 46%|████▌ | 23/50 [00:06<00:07, 3.80it/s] 48%|████▊ | 24/50 [00:06<00:06, 3.79it/s] 50%|█████ | 25/50 [00:06<00:06, 3.79it/s] 52%|█████▏ | 26/50 [00:06<00:06, 3.79it/s] 54%|█████▍ | 27/50 [00:07<00:06, 3.80it/s] 56%|█████▌ | 28/50 [00:07<00:05, 3.80it/s] 58%|█████▊ | 29/50 [00:07<00:05, 3.80it/s] 60%|██████ | 30/50 [00:07<00:05, 3.80it/s] 62%|██████▏ | 31/50 [00:08<00:05, 3.79it/s] 64%|██████▍ | 32/50 [00:08<00:04, 3.78it/s] 66%|██████▌ | 33/50 [00:08<00:04, 3.78it/s] 68%|██████▊ | 34/50 [00:08<00:04, 3.80it/s] 70%|███████ | 35/50 [00:09<00:03, 3.82it/s] 72%|███████▏ | 36/50 [00:09<00:03, 3.81it/s] 74%|███████▍ | 37/50 [00:09<00:03, 3.81it/s] 76%|███████▌ | 38/50 [00:09<00:03, 3.80it/s] 78%|███████▊ | 39/50 [00:10<00:02, 3.79it/s] 80%|████████ | 40/50 [00:10<00:02, 3.80it/s] 82%|████████▏ | 41/50 [00:10<00:02, 3.81it/s] 84%|████████▍ | 42/50 [00:11<00:02, 3.81it/s] 86%|████████▌ | 43/50 [00:11<00:01, 3.80it/s] 88%|████████▊ | 44/50 [00:11<00:01, 3.80it/s] 90%|█████████ | 45/50 [00:11<00:01, 3.81it/s] 92%|█████████▏| 46/50 [00:12<00:01, 3.80it/s] 94%|█████████▍| 47/50 [00:12<00:00, 3.79it/s] 96%|█████████▌| 48/50 [00:12<00:00, 3.80it/s] 98%|█████████▊| 49/50 [00:12<00:00, 3.81it/s] 100%|██████████| 50/50 [00:13<00:00, 3.82it/s] 100%|██████████| 50/50 [00:13<00:00, 3.81it/s] Total safe images: 1 out of 1
Version Details
- Version ID
1e252a4c96aed613339ca8af3de665acb8b584caf41c37bdb05ea331bb36383c- Version Created
- July 14, 2025