mayoita/gloria 🖼️🔢❓📝✓ → 🖼️

▶️ 219 runs 📅 Jun 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"gloria in a sleek, black, futuristic space suit with glossy fabric accents is seen from the waist up behind a high-tech DJ console. Her hands are interacting with glowing touchscreens and holographic controls. She is smiling directly at the camera. The scene takes place inside a spaceship cockpit with metallic walls, bathed in dark tones illuminated by vibrant neon lights in purple, blue, and pink. Behind her, a large circular window reveals a breathtaking view of Earth floating in the deep blackness of space. The overall mood is dark, immersive, and rich with vivid neon glow — a fusion of sci-fi and cyberpunk aesthetics."

Output

Performance Metrics

14.50s Prediction Time

18.52s Total Time

All Input Parameters

{
  "image": "https://replicate.delivery/pbxt/N8MTWOzgU9d70r8szO8SuFT5jLcvEqMSTan89TJCmOTdHUGY/Shot%205.jpeg",
  "model": "dev",
  "prompt": "gloria in a sleek, black, futuristic space suit with glossy fabric accents is seen from the waist up behind a high-tech DJ console. Her hands are interacting with glowing touchscreens and holographic controls. She is smiling directly at the camera. The scene takes place inside a spaceship cockpit with metallic walls, bathed in dark tones illuminated by vibrant neon lights in purple, blue, and pink. Behind her, a large circular window reveals a breathtaking view of Earth floating in the deep blackness of space. The overall mood is dark, immersive, and rich with vivid neon glow — a fusion of sci-fi and cyberpunk aesthetics.",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "16:9",
  "output_format": "jpg",
  "guidance_scale": 3,
  "output_quality": 80,
  "prompt_strength": 0.91,
  "extra_lora_scale": 1,
  "num_inference_steps": 47
}

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

free=27461764657152
Downloading weights
2025-06-05T15:48:35Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpmhdbg612/weights url=https://replicate.delivery/xezq/uXmzMfwUny2kKSDToMOUKvQW4KFLFeftMhEoEAI8BoT6YsnpA/flux-lora.tar
2025-06-05T15:48:35Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-06-05T15:48:35Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/uXmzMfwUny2kKSDToMOUKvQW4KFLFeftMhEoEAI8BoT6YsnpA/flux-lora.tar url=https://replicate.delivery/xezq/uXmzMfwUny2kKSDToMOUKvQW4KFLFeftMhEoEAI8BoT6YsnpA/flux-lora.tar
2025-06-05T15:48:35Z | INFO  | [ Redirect ] redirect_url=http://r8-east4-loras-ric1.cwlota.com/b968fa26d7c7f034da2ba99bcb7e2da9431b3ca35ea3a2a6ae7be9836a21fb9d?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250605%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250605T154835Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=92b5a95124e5a1b4b1b1aba533b41435be97962810e9a45d4949c2d34e10207a url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/uXmzMfwUny2kKSDToMOUKvQW4KFLFeftMhEoEAI8BoT6YsnpA/flux-lora.tar
2025-06-05T15:48:36Z | INFO  | [ Complete ] dest=/tmp/tmpmhdbg612/weights size="172 MB" total_elapsed=0.309s url=https://replicate.delivery/xezq/uXmzMfwUny2kKSDToMOUKvQW4KFLFeftMhEoEAI8BoT6YsnpA/flux-lora.tar
Downloaded weights in 0.37s
Loaded LoRAs in 0.90s
Using seed: 51235
Prompt: gloria in a sleek, black, futuristic space suit with glossy fabric accents is seen from the waist up behind a high-tech DJ console. Her hands are interacting with glowing touchscreens and holographic controls. She is smiling directly at the camera. The scene takes place inside a spaceship cockpit with metallic walls, bathed in dark tones illuminated by vibrant neon lights in purple, blue, and pink. Behind her, a large circular window reveals a breathtaking view of Earth floating in the deep blackness of space. The overall mood is dark, immersive, and rich with vivid neon glow — a fusion of sci-fi and cyberpunk aesthetics.
Input image size: 1408x792
[!] Resizing input image from 1408x792 to 1408x800
[!] img2img mode
  0%|          | 0/43 [00:00<?, ?it/s]
  2%|▏         | 1/43 [00:00<00:09,  4.38it/s]
  5%|▍         | 2/43 [00:00<00:10,  3.80it/s]
  7%|▋         | 3/43 [00:00<00:10,  3.65it/s]
  9%|▉         | 4/43 [00:01<00:10,  3.58it/s]
 12%|█▏        | 5/43 [00:01<00:10,  3.56it/s]
 14%|█▍        | 6/43 [00:01<00:10,  3.53it/s]
 16%|█▋        | 7/43 [00:01<00:10,  3.51it/s]
 19%|█▊        | 8/43 [00:02<00:10,  3.49it/s]
 21%|██        | 9/43 [00:02<00:09,  3.49it/s]
 23%|██▎       | 10/43 [00:02<00:09,  3.50it/s]
 26%|██▌       | 11/43 [00:03<00:09,  3.49it/s]
 28%|██▊       | 12/43 [00:03<00:08,  3.48it/s]
 30%|███       | 13/43 [00:03<00:08,  3.48it/s]
 33%|███▎      | 14/43 [00:03<00:08,  3.49it/s]
 35%|███▍      | 15/43 [00:04<00:08,  3.48it/s]
 37%|███▋      | 16/43 [00:04<00:07,  3.47it/s]
 40%|███▉      | 17/43 [00:04<00:07,  3.47it/s]
 42%|████▏     | 18/43 [00:05<00:07,  3.47it/s]
 44%|████▍     | 19/43 [00:05<00:06,  3.48it/s]
 47%|████▋     | 20/43 [00:05<00:06,  3.48it/s]
 49%|████▉     | 21/43 [00:05<00:06,  3.47it/s]
 51%|█████     | 22/43 [00:06<00:06,  3.47it/s]
 53%|█████▎    | 23/43 [00:06<00:05,  3.48it/s]
 56%|█████▌    | 24/43 [00:06<00:05,  3.47it/s]
 58%|█████▊    | 25/43 [00:07<00:05,  3.46it/s]
 60%|██████    | 26/43 [00:07<00:04,  3.46it/s]
 63%|██████▎   | 27/43 [00:07<00:04,  3.46it/s]
 65%|██████▌   | 28/43 [00:07<00:04,  3.46it/s]
 67%|██████▋   | 29/43 [00:08<00:04,  3.46it/s]
 70%|██████▉   | 30/43 [00:08<00:03,  3.46it/s]
 72%|███████▏  | 31/43 [00:08<00:03,  3.47it/s]
 74%|███████▍  | 32/43 [00:09<00:03,  3.48it/s]
 77%|███████▋  | 33/43 [00:09<00:02,  3.48it/s]
 79%|███████▉  | 34/43 [00:09<00:02,  3.48it/s]
 81%|████████▏ | 35/43 [00:10<00:02,  3.47it/s]
 84%|████████▎ | 36/43 [00:10<00:02,  3.48it/s]
 86%|████████▌ | 37/43 [00:10<00:01,  3.47it/s]
 88%|████████▊ | 38/43 [00:10<00:01,  3.47it/s]
 91%|█████████ | 39/43 [00:11<00:01,  3.48it/s]
 93%|█████████▎| 40/43 [00:11<00:00,  3.48it/s]
 95%|█████████▌| 41/43 [00:11<00:00,  3.48it/s]
 98%|█████████▊| 42/43 [00:12<00:00,  3.47it/s]
100%|██████████| 43/43 [00:12<00:00,  3.47it/s]
100%|██████████| 43/43 [00:12<00:00,  3.49it/s]
Total safe images: 1 out of 1

Version Details

Version ID: bc3c0e6632904975f9b0432ca2b6e8d5ebe3c798bb6fc55b8ba247d7d20b5aa4
Version Created: June 5, 2025

Run on Replicate →