melmoore24/mel 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
Full-body sideview portrait of Mel turned sideways and seated on a stool. Bald head, goatee, honey-tortoise glasses, fit body, linen shirt with rolled sleeves, tailored vest, pants, and shoes — smart-casual style, clapping mid-motion with a big smile, head up, shoulders relaxed.
Highly photorealistic, Natural lighting, studio portrait with a plain background, shot with a full-frame DSLR and, using a prime lens with a wide aperture 50mm f/1.4 lens. Shallow depth of field, realistic skin pores, micro-hair strands, natural grain, slight asymmetry, and fabric folds. Background softly blurred with true optical depth, rendered in 8K cinematic quality.
"Output
Performance Metrics
11.25s
Prediction Time
12.68s
Total Time
All Input Parameters
{
"mask": "https://replicate.delivery/pbxt/NfjZ1epXUrnx6IAaSvFw8Qas9tNyb2VdlaK2IGOLYZt3UEDf/out-0%20%2883%29.webp",
"model": "dev",
"prompt": "Full-body sideview portrait of Mel turned sideways and seated on a stool. Bald head, goatee, honey-tortoise glasses, fit body, linen shirt with rolled sleeves, tailored vest, pants, and shoes — smart-casual style, clapping mid-motion with a big smile, head up, shoulders relaxed.\n\nHighly photorealistic, Natural lighting, studio portrait with a plain background, shot with a full-frame DSLR and, using a prime lens with a wide aperture 50mm f/1.4 lens. Shallow depth of field, realistic skin pores, micro-hair strands, natural grain, slight asymmetry, and fabric folds. Background softly blurred with true optical depth, rendered in 8K cinematic quality.",
"go_fast": false,
"lora_scale": 1.083,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 2.45,
"output_quality": 80,
"prompt_strength": 0.51,
"extra_lora_scale": 1,
"num_inference_steps": 39
}
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
Loaded LoRAs in 0.53s Using seed: 54538 Prompt: Full-body sideview portrait of Mel turned sideways and seated on a stool. Bald head, goatee, honey-tortoise glasses, fit body, linen shirt with rolled sleeves, tailored vest, pants, and shoes — smart-casual style, clapping mid-motion with a big smile, head up, shoulders relaxed. Highly photorealistic, Natural lighting, studio portrait with a plain background, shot with a full-frame DSLR and, using a prime lens with a wide aperture 50mm f/1.4 lens. Shallow depth of field, realistic skin pores, micro-hair strands, natural grain, slight asymmetry, and fabric folds. Background softly blurred with true optical depth, rendered in 8K cinematic quality. [!] txt2img mode 0%| | 0/39 [00:00<?, ?it/s] 3%|▎ | 1/39 [00:00<00:10, 3.72it/s] 5%|▌ | 2/39 [00:00<00:08, 4.13it/s] 8%|▊ | 3/39 [00:00<00:09, 3.99it/s] 10%|█ | 4/39 [00:01<00:08, 3.93it/s] 13%|█▎ | 5/39 [00:01<00:08, 3.90it/s] 15%|█▌ | 6/39 [00:01<00:08, 3.86it/s] 18%|█▊ | 7/39 [00:01<00:08, 3.85it/s] 21%|██ | 8/39 [00:02<00:08, 3.84it/s] 23%|██▎ | 9/39 [00:02<00:07, 3.83it/s] 26%|██▌ | 10/39 [00:02<00:07, 3.83it/s] 28%|██▊ | 11/39 [00:02<00:07, 3.82it/s] 31%|███ | 12/39 [00:03<00:07, 3.82it/s] 33%|███▎ | 13/39 [00:03<00:06, 3.81it/s] 36%|███▌ | 14/39 [00:03<00:06, 3.82it/s] 38%|███▊ | 15/39 [00:03<00:06, 3.81it/s] 41%|████ | 16/39 [00:04<00:06, 3.82it/s] 44%|████▎ | 17/39 [00:04<00:05, 3.82it/s] 46%|████▌ | 18/39 [00:04<00:05, 3.82it/s] 49%|████▊ | 19/39 [00:04<00:05, 3.82it/s] 51%|█████▏ | 20/39 [00:05<00:04, 3.82it/s] 54%|█████▍ | 21/39 [00:05<00:04, 3.82it/s] 56%|█████▋ | 22/39 [00:05<00:04, 3.81it/s] 59%|█████▉ | 23/39 [00:05<00:04, 3.82it/s] 62%|██████▏ | 24/39 [00:06<00:03, 3.83it/s] 64%|██████▍ | 25/39 [00:06<00:03, 3.83it/s] 67%|██████▋ | 26/39 [00:06<00:03, 3.82it/s] 69%|██████▉ | 27/39 [00:07<00:03, 3.82it/s] 72%|███████▏ | 28/39 [00:07<00:02, 3.82it/s] 74%|███████▍ | 29/39 [00:07<00:02, 3.82it/s] 77%|███████▋ | 30/39 [00:07<00:02, 3.81it/s] 79%|███████▉ | 31/39 [00:08<00:02, 3.81it/s] 82%|████████▏ | 32/39 [00:08<00:01, 3.81it/s] 85%|████████▍ | 33/39 [00:08<00:01, 3.81it/s] 87%|████████▋ | 34/39 [00:08<00:01, 3.81it/s] 90%|████████▉ | 35/39 [00:09<00:01, 3.82it/s] 92%|█████████▏| 36/39 [00:09<00:00, 3.81it/s] 95%|█████████▍| 37/39 [00:09<00:00, 3.81it/s] 97%|█████████▋| 38/39 [00:09<00:00, 3.81it/s] 100%|██████████| 39/39 [00:10<00:00, 3.82it/s] 100%|██████████| 39/39 [00:10<00:00, 3.83it/s] Total safe images: 1 out of 1
Version Details
- Version ID
78cf3ae563289761c71c77869eacde9eb159447a7c35de7e4f725bd3aadcef36- Version Created
- September 7, 2025