mrtomollerton/m-m-m 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
Create a realistic visual of a south korean middle aged lady looking at the camera. Do not include lettering or any type of logo or brand reference.
The image must be bright and dominated by white and luminous, full of light, filled with positive energy.
Use the red colour,, black, and white only. White should cover 70% of the image, red 25% and black even less.
High fidelity authentic and real images.
The setting is modern and sleek, emphasizing clean lines and high-tech aesthetics.
Include a shallow depth of field for a blurred background effect, emulating a DSLR camera, using a 50mm lens at f/1.8 for a shallow depth of field
Composition: Use rule of thirds, framing, and perspective
Strictly avoiding stylized, cartoonish, or exaggerated features, ensuring a realistic human portrayal. Avoid cartoonish, animated, or exaggerated styles. The image must look indistinguishable from a real photograph.
Output
Performance Metrics
6.49s
Prediction Time
6.69s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "Create a realistic visual of a south korean middle aged lady looking at the camera. Do not include lettering or any type of logo or brand reference. \n\nThe image must be bright and dominated by white and luminous, full of light, filled with positive energy.\n\nUse the red colour,, black, and white only. White should cover 70% of the image, red 25% and black even less.\n\nHigh fidelity authentic and real images.\n\nThe setting is modern and sleek, emphasizing clean lines and high-tech aesthetics. \n\nInclude a shallow depth of field for a blurred background effect, emulating a DSLR camera, using a 50mm lens at f/1.8 for a shallow depth of field\nComposition: Use rule of thirds, framing, and perspective \nStrictly avoiding stylized, cartoonish, or exaggerated features, ensuring a realistic human portrayal. Avoid cartoonish, animated, or exaggerated styles. The image must look indistinguishable from a real photograph.\n",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 3,
"output_quality": 80,
"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
2024-12-13 13:18:41.331 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2024-12-13 13:18:41.331 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 88%|████████▊ | 268/304 [00:00<00:00, 2667.42it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2552.38it/s] 2024-12-13 13:18:41.451 | SUCCESS | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s 2024-12-13 13:18:41.453 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/831c93c09d5eac82 2024-12-13 13:18:41.566 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded 2024-12-13 13:18:41.566 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2024-12-13 13:18:41.566 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 88%|████████▊ | 268/304 [00:00<00:00, 2669.20it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2553.83it/s] 2024-12-13 13:18:41.686 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.23s Using seed: 47626 0it [00:00, ?it/s] 1it [00:00, 8.30it/s] 2it [00:00, 5.80it/s] 3it [00:00, 5.29it/s] 4it [00:00, 5.09it/s] 5it [00:00, 4.97it/s] 6it [00:01, 4.89it/s] 7it [00:01, 4.84it/s] 8it [00:01, 4.82it/s] 9it [00:01, 4.81it/s] 10it [00:02, 4.80it/s] 11it [00:02, 4.79it/s] 12it [00:02, 4.79it/s] 13it [00:02, 4.78it/s] 14it [00:02, 4.78it/s] 15it [00:03, 4.78it/s] 16it [00:03, 4.78it/s] 17it [00:03, 4.77it/s] 18it [00:03, 4.77it/s] 19it [00:03, 4.77it/s] 20it [00:04, 4.77it/s] 21it [00:04, 4.76it/s] 22it [00:04, 4.76it/s] 23it [00:04, 4.76it/s] 24it [00:04, 4.77it/s] 25it [00:05, 4.77it/s] 26it [00:05, 4.76it/s] 27it [00:05, 4.76it/s] 28it [00:05, 4.76it/s] 28it [00:05, 4.84it/s] Total safe images: 1 out of 1
Version Details
- Version ID
4418802c858c3e015cbc4e6751745916f8a54b51095e06d20e009051607b5b24- Version Created
- December 13, 2024