swk23/grievous 🖼️🔢❓📝✓ → 🖼️

▶️ 40 runs 📅 Dec 2024 ⚙️ Cog 0.11.1

About

Example Output

Prompt:

""A close-up headshot of General Grievous in the dimly lit hallway of a Venator-class Star Destroyer, his sinister mechanical face illuminated by the flickering emergency lights. His piercing yellow eyes glow menacingly, exuding a sense of danger and cunning. The red hue of the ship’s alert systems casts an ominous light across his metallic features, highlighting the intricate details of his cybernetic design. Sparks fly from damaged panels behind him, while a light haze of smoke swirls around, adding depth and tension to the scene. The atmosphere is cinematic and photorealistic, capturing the essence of Star Wars.""

Output

Performance Metrics

7.50s Prediction Time

8.08s Total Time

All Input Parameters

{
  "model": "dev",
  "prompt": "\"A close-up headshot of General Grievous in the dimly lit hallway of a Venator-class Star Destroyer, his sinister mechanical face illuminated by the flickering emergency lights. His piercing yellow eyes glow menacingly, exuding a sense of danger and cunning. The red hue of the ship’s alert systems casts an ominous light across his metallic features, highlighting the intricate details of his cybernetic design. Sparks fly from damaged panels behind him, while a light haze of smoke swirls around, adding depth and tension to the scene. The atmosphere is cinematic and photorealistic, capturing the essence of Star Wars.\"",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "21:9",
  "output_format": "webp",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

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

2025-01-04 09:12:03.697 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-04 09:12:03.698 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2749.32it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2671.22it/s]
2025-01-04 09:12:03.812 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-04 09:12:03.812 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  65%|██████▍   | 197/304 [00:00<00:00, 1949.36it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 1869.82it/s]
2025-01-04 09:12:03.975 | SUCCESS  | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.28s
free=29253508792320
Downloading weights
2025-01-04T09:12:03Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmphvcsvcvq/weights url=https://replicate.delivery/xezq/bPzjYmCcozquIZgamAEbVRRMt0gna8OxAKBVMvECCO4UQEeJA/trained_model.tar
2025-01-04T09:12:05Z | INFO  | [ Complete ] dest=/tmp/tmphvcsvcvq/weights size="172 MB" total_elapsed=1.403s url=https://replicate.delivery/xezq/bPzjYmCcozquIZgamAEbVRRMt0gna8OxAKBVMvECCO4UQEeJA/trained_model.tar
Downloaded weights in 1.43s
2025-01-04 09:12:05.404 | INFO     | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/ed8f308750fe8013
2025-01-04 09:12:05.474 | INFO     | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded
2025-01-04 09:12:05.474 | DEBUG    | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys
2025-01-04 09:12:05.474 | DEBUG    | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted
Applying LoRA:   0%|          | 0/304 [00:00<?, ?it/s]
Applying LoRA:  91%|█████████ | 276/304 [00:00<00:00, 2759.43it/s]
Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2680.20it/s]
2025-01-04 09:12:05.588 | SUCCESS  | fp8.lora_loading:load_lora:539 - LoRA applied in 0.18s
Using seed: 54980
0it [00:00, ?it/s]
1it [00:00,  9.09it/s]
2it [00:00,  6.40it/s]
3it [00:00,  5.85it/s]
4it [00:00,  5.62it/s]
5it [00:00,  5.50it/s]
6it [00:01,  5.40it/s]
7it [00:01,  5.34it/s]
8it [00:01,  5.30it/s]
9it [00:01,  5.25it/s]
10it [00:01,  5.27it/s]
11it [00:02,  5.27it/s]
12it [00:02,  5.28it/s]
13it [00:02,  5.26it/s]
14it [00:02,  5.23it/s]
15it [00:02,  5.23it/s]
16it [00:02,  5.22it/s]
17it [00:03,  5.24it/s]
18it [00:03,  5.24it/s]
19it [00:03,  5.21it/s]
20it [00:03,  5.22it/s]
21it [00:03,  5.23it/s]
22it [00:04,  5.21it/s]
23it [00:04,  5.22it/s]
24it [00:04,  5.24it/s]
25it [00:04,  5.22it/s]
26it [00:04,  5.23it/s]
27it [00:05,  5.22it/s]
28it [00:05,  5.21it/s]
28it [00:05,  5.32it/s]
Total safe images: 1 out of 1

Version Details

Version ID: 1669af1e82695d534e463f9ed922571da0507046d056d69ee59081861c18dc23
Version Created: December 6, 2024

Run on Replicate →