merlintxu/matahari 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"a photo of MataHari dancing in a restaurant salon "
Output
Performance Metrics
34.62s
Prediction Time
34.65s
Total Time
All Input Parameters
{
"model": "dev",
"width": 1024,
"height": 768,
"prompt": "a photo of MataHari dancing in a restaurant salon ",
"lora_scale": 1,
"num_outputs": 4,
"aspect_ratio": "16:9",
"output_format": "webp",
"guidance_scale": 3.5,
"output_quality": 100,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 25
}
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
Using seed: 13861 Prompt: a photo of MataHari dancing in a restaurant salon [!] txt2img mode Using dev model free=29772396552192 Downloading weights 2024-11-11T14:09:17Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmphcaxn1e8/weights url=https://replicate.delivery/xezq/TY62mJuhFSKmOptTSNNrI0BCTo5lelP1Fmlr2mYiJBMuf7vTA/trained_model.tar 2024-11-11T14:09:19Z | INFO | [ Complete ] dest=/tmp/tmphcaxn1e8/weights size="269 MB" total_elapsed=2.092s url=https://replicate.delivery/xezq/TY62mJuhFSKmOptTSNNrI0BCTo5lelP1Fmlr2mYiJBMuf7vTA/trained_model.tar Downloaded weights in 2.12s Loaded LoRAs in 2.58s 0%| | 0/25 [00:00<?, ?it/s] 4%|▍ | 1/25 [00:01<00:29, 1.24s/it] 8%|▊ | 2/25 [00:02<00:25, 1.11s/it] 12%|█▏ | 3/25 [00:03<00:25, 1.17s/it] 16%|█▌ | 4/25 [00:04<00:25, 1.20s/it] 20%|██ | 5/25 [00:05<00:24, 1.22s/it] 24%|██▍ | 6/25 [00:07<00:23, 1.22s/it] 28%|██▊ | 7/25 [00:08<00:22, 1.23s/it] 32%|███▏ | 8/25 [00:09<00:21, 1.24s/it] 36%|███▌ | 9/25 [00:10<00:19, 1.24s/it] 40%|████ | 10/25 [00:12<00:18, 1.24s/it] 44%|████▍ | 11/25 [00:13<00:17, 1.24s/it] 48%|████▊ | 12/25 [00:14<00:16, 1.24s/it] 52%|█████▏ | 13/25 [00:15<00:14, 1.24s/it] 56%|█████▌ | 14/25 [00:17<00:13, 1.24s/it] 60%|██████ | 15/25 [00:18<00:12, 1.24s/it] 64%|██████▍ | 16/25 [00:19<00:11, 1.25s/it] 68%|██████▊ | 17/25 [00:20<00:09, 1.24s/it] 72%|███████▏ | 18/25 [00:22<00:08, 1.24s/it] 76%|███████▌ | 19/25 [00:23<00:07, 1.25s/it] 80%|████████ | 20/25 [00:24<00:06, 1.24s/it] 84%|████████▍ | 21/25 [00:25<00:04, 1.24s/it] 88%|████████▊ | 22/25 [00:27<00:03, 1.24s/it] 92%|█████████▏| 23/25 [00:28<00:02, 1.24s/it] 96%|█████████▌| 24/25 [00:29<00:01, 1.25s/it] 100%|██████████| 25/25 [00:30<00:00, 1.25s/it] 100%|██████████| 25/25 [00:30<00:00, 1.24s/it]
Version Details
- Version ID
53eaf5246ec96ecc9fa0138d2618f61449b560cd105fb9dfaca1b436c774970d- Version Created
- November 11, 2024