jaaacki/simonng 🖼️🔢❓📝✓ → 🖼️

▶️ 18 runs 📅 Sep 2024 ⚙️ Cog 0.9.23

About

Example Output

Prompt:

"A cinematic, action-packed scene featuring HENRYHO as Neo and SIMONNG as Morpheus from The Matrix. Both characters are captured in a close-up shot, their intense expressions highlighting the gravity of the moment. HENRYHO, portraying Neo, wears the iconic black trench coat and sleek sunglasses, his gaze sharp and focused. Beside him, SIMONNG embodies Morpheus, donning the classic long leather coat, mirrored sunglasses, and exuding a calm yet commanding presence. The background is alive with cascading green Matrix code and a moody, futuristic cityscape. Dynamic elements like bullets suspended mid-air and swirling fragments of digital code add energy to the scene. The lighting casts dramatic shadows, emphasizing the contours of their faces and the tension of the moment. The camera angle centers on both characters, showcasing their partnership and capturing the thrilling essence of The Matrix in a visually stunning image."

Output

Performance Metrics

36.80s Prediction Time

117.73s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "A cinematic, action-packed scene featuring HENRYHO as Neo and SIMONNG as Morpheus from The Matrix. Both characters are captured in a close-up shot, their intense expressions highlighting the gravity of the moment. HENRYHO, portraying Neo, wears the iconic black trench coat and sleek sunglasses, his gaze sharp and focused. Beside him, SIMONNG embodies Morpheus, donning the classic long leather coat, mirrored sunglasses, and exuding a calm yet commanding presence. The background is alive with cascading green Matrix code and a moody, futuristic cityscape. Dynamic elements like bullets suspended mid-air and swirling fragments of digital code add energy to the scene. The lighting casts dramatic shadows, emphasizing the contours of their faces and the tension of the moment. The camera angle centers on both characters, showcasing their partnership and capturing the thrilling essence of The Matrix in a visually stunning image.",
  "extra_lora": "jaaacki/henryho",
  "lora_scale": 0.7,
  "num_outputs": 1,
  "aspect_ratio": "1:1",
  "output_format": "png",
  "guidance_scale": 3.5,
  "output_quality": 90,
  "prompt_strength": 0.92,
  "extra_lora_scale": 1,
  "num_inference_steps": 40
}

Input Parameters

mask Type: string: Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
seed Type: integer: Random seed. Set for reproducible generation
image Type: string: Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored.
model Default: dev: 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 Type: integerRange: 256 - 1440: 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 Type: integerRange: 256 - 1440: 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) Type: string: 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 Type: booleanDefault: false: Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16
extra_lora Type: string: 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 Type: numberDefault: 1Range: -1 - 3: 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 Default: 1: Approximate number of megapixels for generated image
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of outputs to generate
aspect_ratio Default: 1:1: Aspect ratio for the generated image. If custom is selected, uses height and width below & will run in bf16 mode
output_format Default: webp: Format of the output images
guidance_scale Type: numberDefault: 3Range: 0 - 10: 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 Type: integerDefault: 80Range: 0 - 100: 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 Type: numberDefault: 0.8Range: 0 - 1: Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
extra_lora_scale Type: numberDefault: 1Range: -1 - 3: 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 Type: string: 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 Type: integerDefault: 28Range: 1 - 50: Number of denoising steps. More steps can give more detailed images, but take longer.
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images.

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 9435
Prompt: A cinematic, action-packed scene featuring HENRYHO as Neo and SIMONNG as Morpheus from The Matrix. Both characters are captured in a close-up shot, their intense expressions highlighting the gravity of the moment. HENRYHO, portraying Neo, wears the iconic black trench coat and sleek sunglasses, his gaze sharp and focused. Beside him, SIMONNG embodies Morpheus, donning the classic long leather coat, mirrored sunglasses, and exuding a calm yet commanding presence. The background is alive with cascading green Matrix code and a moody, futuristic cityscape. Dynamic elements like bullets suspended mid-air and swirling fragments of digital code add energy to the scene. The lighting casts dramatic shadows, emphasizing the contours of their faces and the tension of the moment. The camera angle centers on both characters, showcasing their partnership and capturing the thrilling essence of The Matrix in a visually stunning image.
[!] txt2img mode
Using dev model
Loading extra LoRA weights from: jaaacki/henryho
free=4015412424704
Downloading weights
2024-09-28T10:58:31Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpwcv_q973/weights url=https://replicate.delivery/yhqm/N8mJxHq9MlooARGB4rfBmfgYutfo3C4fDXHD7q0ceEuB9yFcC/trained_model.tar
2024-09-28T10:58:32Z | INFO  | [ Complete ] dest=/tmp/tmpwcv_q973/weights size="172 MB" total_elapsed=1.412s url=https://replicate.delivery/yhqm/N8mJxHq9MlooARGB4rfBmfgYutfo3C4fDXHD7q0ceEuB9yFcC/trained_model.tar
Downloaded weights in 1.44s
free=4015239876608
Downloading weights
2024-09-28T10:58:32Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp1hmvs29a/weights url=https://replicate.com/jaaacki/henryho/_weights
2024-09-28T10:58:33Z | INFO  | [ Redirect ] redirect_url=https://replicate.delivery/yhqm/WafiqLhxDOwxUCbf5WnHLVIQDFnXuvhNJDeXoep3qKLishFOB/trained_model.tar url=https://replicate.com/jaaacki/henryho/_weights
2024-09-28T10:58:36Z | INFO  | [ Complete ] dest=/tmp/tmp1hmvs29a/weights size="172 MB" total_elapsed=3.423s url=https://replicate.com/jaaacki/henryho/_weights
Downloaded weights in 3.46s
Loaded LoRAs in 6.40s
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:28,  1.36it/s]
  5%|▌         | 2/40 [00:01<00:25,  1.49it/s]
  8%|▊         | 3/40 [00:02<00:25,  1.43it/s]
 10%|█         | 4/40 [00:02<00:25,  1.40it/s]
 12%|█▎        | 5/40 [00:03<00:25,  1.39it/s]
 15%|█▌        | 6/40 [00:04<00:24,  1.38it/s]
 18%|█▊        | 7/40 [00:05<00:24,  1.37it/s]
 20%|██        | 8/40 [00:05<00:23,  1.37it/s]
 22%|██▎       | 9/40 [00:06<00:22,  1.36it/s]
 25%|██▌       | 10/40 [00:07<00:22,  1.36it/s]
 28%|██▊       | 11/40 [00:07<00:21,  1.36it/s]
 30%|███       | 12/40 [00:08<00:20,  1.36it/s]
 32%|███▎      | 13/40 [00:09<00:19,  1.36it/s]
 35%|███▌      | 14/40 [00:10<00:19,  1.36it/s]
 38%|███▊      | 15/40 [00:10<00:18,  1.36it/s]
 40%|████      | 16/40 [00:11<00:17,  1.36it/s]
 42%|████▎     | 17/40 [00:12<00:16,  1.36it/s]
 45%|████▌     | 18/40 [00:13<00:16,  1.36it/s]
 48%|████▊     | 19/40 [00:13<00:15,  1.36it/s]
 50%|█████     | 20/40 [00:14<00:14,  1.36it/s]
 52%|█████▎    | 21/40 [00:15<00:13,  1.36it/s]
 55%|█████▌    | 22/40 [00:16<00:13,  1.36it/s]
 57%|█████▊    | 23/40 [00:16<00:12,  1.36it/s]
 60%|██████    | 24/40 [00:17<00:11,  1.36it/s]
 62%|██████▎   | 25/40 [00:18<00:11,  1.36it/s]
 65%|██████▌   | 26/40 [00:19<00:10,  1.36it/s]
 68%|██████▊   | 27/40 [00:19<00:09,  1.36it/s]
 70%|███████   | 28/40 [00:20<00:08,  1.36it/s]
 72%|███████▎  | 29/40 [00:21<00:08,  1.36it/s]
 75%|███████▌  | 30/40 [00:21<00:07,  1.36it/s]
 78%|███████▊  | 31/40 [00:22<00:06,  1.36it/s]
 80%|████████  | 32/40 [00:23<00:05,  1.36it/s]
 82%|████████▎ | 33/40 [00:24<00:05,  1.36it/s]
 85%|████████▌ | 34/40 [00:24<00:04,  1.36it/s]
 88%|████████▊ | 35/40 [00:25<00:03,  1.36it/s]
 90%|█████████ | 36/40 [00:26<00:02,  1.36it/s]
 92%|█████████▎| 37/40 [00:27<00:02,  1.36it/s]
 95%|█████████▌| 38/40 [00:27<00:01,  1.36it/s]
 98%|█████████▊| 39/40 [00:28<00:00,  1.36it/s]
100%|██████████| 40/40 [00:29<00:00,  1.36it/s]
100%|██████████| 40/40 [00:29<00:00,  1.36it/s]

Version Details

Version ID: 1b94a5cff4cf221a11702b2ad557dda7e8deb5f6e7feb7f13075e01a0aee0838
Version Created: September 26, 2024

Run on Replicate →