downlifted/justspooky-halloween-flux-bewiz 🖼️🔢❓📝✓ → 🖼️
About
JUSTSPOOKY is a collection of 500 carefully selected images, put together to create some of the best spooky vibes you can get. I spent a lot of time finding and curating these, so I hope you enjoy the results.
Example Output
Prompt:
"JUSTSPOOKY: A grotesque carnival where the clowns are not just creepy—they're murderous. Their grinning faces are smeared with blood, and they carry rusted knives dripping with gore. The funhouse is a maze of mirrors, each reflecting a more horrifying version of yourself, while the Ferris wheel is made of bones and sinew."
Output
Performance Metrics
35.96s
Prediction Time
91.65s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "JUSTSPOOKY: A grotesque carnival where the clowns are not just creepy—they're murderous. Their grinning faces are smeared with blood, and they carry rusted knives dripping with gore. The funhouse is a maze of mirrors, each reflecting a more horrifying version of yourself, while the Ferris wheel is made of bones and sinew.\n\n\n\n\n\n\n",
"lora_scale": 0.95,
"num_outputs": 2,
"aspect_ratio": "1:1",
"output_format": "png",
"guidance_scale": 2.01,
"output_quality": 100,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 45
}
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: 34055 Prompt: JUSTSPOOKY: A grotesque carnival where the clowns are not just creepy—they're murderous. Their grinning faces are smeared with blood, and they carry rusted knives dripping with gore. The funhouse is a maze of mirrors, each reflecting a more horrifying version of yourself, while the Ferris wheel is made of bones and sinew. [!] txt2img mode Using dev model free=6493280063488 Downloading weights 2024-09-24T11:09:57Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpki32aikw/weights url=https://replicate.delivery/yhqm/q8VvkoFqck6DDRIvoRg4TElTLjg6GflNfp86fwbe4n4Sy4fbC/trained_model.tar 2024-09-24T11:09:59Z | INFO | [ Complete ] dest=/tmp/tmpki32aikw/weights size="215 MB" total_elapsed=1.488s url=https://replicate.delivery/yhqm/q8VvkoFqck6DDRIvoRg4TElTLjg6GflNfp86fwbe4n4Sy4fbC/trained_model.tar Downloaded weights in 1.52s Loaded LoRAs in 9.36s 0%| | 0/45 [00:00<?, ?it/s] 2%|▏ | 1/45 [00:00<00:24, 1.78it/s] 4%|▍ | 2/45 [00:01<00:21, 1.99it/s] 7%|▋ | 3/45 [00:01<00:22, 1.90it/s] 9%|▉ | 4/45 [00:02<00:22, 1.86it/s] 11%|█ | 5/45 [00:02<00:21, 1.84it/s] 13%|█▎ | 6/45 [00:03<00:21, 1.83it/s] 16%|█▌ | 7/45 [00:03<00:20, 1.82it/s] 18%|█▊ | 8/45 [00:04<00:20, 1.82it/s] 20%|██ | 9/45 [00:04<00:19, 1.82it/s] 22%|██▏ | 10/45 [00:05<00:19, 1.81it/s] 24%|██▍ | 11/45 [00:06<00:18, 1.81it/s] 27%|██▋ | 12/45 [00:06<00:18, 1.81it/s] 29%|██▉ | 13/45 [00:07<00:17, 1.81it/s] 31%|███ | 14/45 [00:07<00:17, 1.81it/s] 33%|███▎ | 15/45 [00:08<00:16, 1.81it/s] 36%|███▌ | 16/45 [00:08<00:16, 1.81it/s] 38%|███▊ | 17/45 [00:09<00:15, 1.80it/s] 40%|████ | 18/45 [00:09<00:14, 1.81it/s] 42%|████▏ | 19/45 [00:10<00:14, 1.80it/s] 44%|████▍ | 20/45 [00:10<00:13, 1.81it/s] 47%|████▋ | 21/45 [00:11<00:13, 1.81it/s] 49%|████▉ | 22/45 [00:12<00:12, 1.80it/s] 51%|█████ | 23/45 [00:12<00:12, 1.80it/s] 53%|█████▎ | 24/45 [00:13<00:11, 1.80it/s] 56%|█████▌ | 25/45 [00:13<00:11, 1.80it/s] 58%|█████▊ | 26/45 [00:14<00:10, 1.80it/s] 60%|██████ | 27/45 [00:14<00:09, 1.80it/s] 62%|██████▏ | 28/45 [00:15<00:09, 1.80it/s] 64%|██████▍ | 29/45 [00:15<00:08, 1.80it/s] 67%|██████▋ | 30/45 [00:16<00:08, 1.80it/s] 69%|██████▉ | 31/45 [00:17<00:07, 1.80it/s] 71%|███████ | 32/45 [00:17<00:07, 1.80it/s] 73%|███████▎ | 33/45 [00:18<00:06, 1.80it/s] 76%|███████▌ | 34/45 [00:18<00:06, 1.80it/s] 78%|███████▊ | 35/45 [00:19<00:05, 1.80it/s] 80%|████████ | 36/45 [00:19<00:04, 1.80it/s] 82%|████████▏ | 37/45 [00:20<00:04, 1.80it/s] 84%|████████▍ | 38/45 [00:20<00:03, 1.80it/s] 87%|████████▋ | 39/45 [00:21<00:03, 1.80it/s] 89%|████████▉ | 40/45 [00:22<00:02, 1.80it/s] 91%|█████████ | 41/45 [00:22<00:02, 1.80it/s] 93%|█████████▎| 42/45 [00:23<00:01, 1.80it/s] 96%|█████████▌| 43/45 [00:23<00:01, 1.80it/s] 98%|█████████▊| 44/45 [00:24<00:00, 1.80it/s] 100%|██████████| 45/45 [00:24<00:00, 1.80it/s] 100%|██████████| 45/45 [00:24<00:00, 1.81it/s]
Version Details
- Version ID
f44d81aa9401c7ec7609a0205e5528fd80b08cefd788e2579154b929019a1536- Version Created
- September 24, 2024