biguloff/jason-stathanm 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"JSN in sport store, kodak, MAN.dmg"
Output
Performance Metrics
38.69s
Prediction Time
38.86s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "JSN in sport store, kodak, MAN.dmg",
"lora_scale": 1,
"num_outputs": 4,
"aspect_ratio": "9:16",
"output_format": "png",
"guidance_scale": 3,
"output_quality": 90,
"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
Using seed: 48002 Prompt: JSN in sport store, kodak, MAN.dmg [!] txt2img mode Using dev model free=29181757075456 Downloading weights 2024-11-11T10:20:20Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmp36moknbo/weights url=https://replicate.delivery/xezq/ln4IRm0MmUbAOhaQJD3hG6BOEjhewbhHOEmG2hcPQOr9W83JA/trained_model.tar 2024-11-11T10:20:22Z | INFO | [ Complete ] dest=/tmp/tmp36moknbo/weights size="344 MB" total_elapsed=2.613s url=https://replicate.delivery/xezq/ln4IRm0MmUbAOhaQJD3hG6BOEjhewbhHOEmG2hcPQOr9W83JA/trained_model.tar Downloaded weights in 2.64s Loaded LoRAs in 3.29s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:32, 1.19s/it] 7%|▋ | 2/28 [00:02<00:27, 1.08s/it] 11%|█ | 3/28 [00:03<00:28, 1.13s/it] 14%|█▍ | 4/28 [00:04<00:27, 1.16s/it] 18%|█▊ | 5/28 [00:05<00:26, 1.17s/it] 21%|██▏ | 6/28 [00:06<00:25, 1.18s/it] 25%|██▌ | 7/28 [00:08<00:24, 1.19s/it] 29%|██▊ | 8/28 [00:09<00:23, 1.19s/it] 32%|███▏ | 9/28 [00:10<00:22, 1.19s/it] 36%|███▌ | 10/28 [00:11<00:21, 1.20s/it] 39%|███▉ | 11/28 [00:12<00:20, 1.20s/it] 43%|████▎ | 12/28 [00:14<00:19, 1.20s/it] 46%|████▋ | 13/28 [00:15<00:17, 1.20s/it] 50%|█████ | 14/28 [00:16<00:16, 1.20s/it] 54%|█████▎ | 15/28 [00:17<00:15, 1.20s/it] 57%|█████▋ | 16/28 [00:18<00:14, 1.20s/it] 61%|██████ | 17/28 [00:20<00:13, 1.20s/it] 64%|██████▍ | 18/28 [00:21<00:11, 1.20s/it] 68%|██████▊ | 19/28 [00:22<00:10, 1.20s/it] 71%|███████▏ | 20/28 [00:23<00:09, 1.20s/it] 75%|███████▌ | 21/28 [00:24<00:08, 1.20s/it] 79%|███████▊ | 22/28 [00:26<00:07, 1.20s/it] 82%|████████▏ | 23/28 [00:27<00:05, 1.20s/it] 86%|████████▌ | 24/28 [00:28<00:04, 1.20s/it] 89%|████████▉ | 25/28 [00:29<00:03, 1.20s/it] 93%|█████████▎| 26/28 [00:30<00:02, 1.20s/it] 96%|█████████▋| 27/28 [00:32<00:01, 1.20s/it] 100%|██████████| 28/28 [00:33<00:00, 1.20s/it] 100%|██████████| 28/28 [00:33<00:00, 1.19s/it]
Version Details
- Version ID
95310a9166fde35cb5c3add297cc37a8294d34fbb0366f806e81d83fc513c48a- Version Created
- November 11, 2024