krisdoan/gb2045g 🖼️🔢❓📝✓ → 🖼️

▶️ 350 runs 📅 Aug 2025 ⚙️ Cog 0.13.6

About

Example Output

Prompt:

"a pair of GB2045G eyeglasses wore by a young Japanese woman, summer vibe, realistic, studio style"

Output

Performance Metrics

16.36s Prediction Time

18.70s Total Time

All Input Parameters

{
  "model": "dev",
  "width": 1440,
  "height": 1440,
  "prompt": "a pair of GB2045G eyeglasses wore by a young Japanese woman, summer vibe, realistic, studio style",
  "go_fast": false,
  "extra_lora": "https://huggingface.co/PlayDustinDB/FLUX.1-Krea-dev-LoRA/resolve/main/flux1-krea-dev_rank_128-bf16.safetensors",
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 1,
  "aspect_ratio": "9:16",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 0.8,
  "num_inference_steps": 35
}

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=23591079550976
Downloading weights
2025-08-29T02:21:13Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmp4q7x8vf2/weights url=https://replicate.delivery/xezq/cUxMlh24OeTyK6CBYrEfkhC7LQe18c229wfHOlotO4HHCwepC/flux-lora.tar
2025-08-29T02:21:13Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-08-29T02:21:13Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/cUxMlh24OeTyK6CBYrEfkhC7LQe18c229wfHOlotO4HHCwepC/flux-lora.tar url=https://replicate.delivery/xezq/cUxMlh24OeTyK6CBYrEfkhC7LQe18c229wfHOlotO4HHCwepC/flux-lora.tar
2025-08-29T02:21:13Z | INFO  | [ Redirect ] redirect_url=https://replicate.delivery/xezq/cUxMlh24OeTyK6CBYrEfkhC7LQe18c229wfHOlotO4HHCwepC/flux-lora.tar url=http://hermes.services.svc.cluster.local/replicate.delivery/xezq/cUxMlh24OeTyK6CBYrEfkhC7LQe18c229wfHOlotO4HHCwepC/flux-lora.tar
2025-08-29T02:21:15Z | INFO  | [ Complete ] dest=/tmp/tmp4q7x8vf2/weights size="172 MB" total_elapsed=2.518s url=https://replicate.delivery/xezq/cUxMlh24OeTyK6CBYrEfkhC7LQe18c229wfHOlotO4HHCwepC/flux-lora.tar
Downloaded weights in 2.58s
free=23590906056704
Downloading weights
2025-08-29T02:21:16Z | INFO  | [ Initiating ] chunk_size=150M dest=/src/weights-cache/0d403bf300e3c590 url=https://huggingface.co/PlayDustinDB/FLUX.1-Krea-dev-LoRA/resolve/main/flux1-krea-dev_rank_128-bf16.safetensors
2025-08-29T02:21:16Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-08-29T02:21:16Z | INFO  | [ Cache URL Rewrite ] enabled=true target_url=http://hermes.services.svc.cluster.local/huggingface.co/PlayDustinDB/FLUX.1-Krea-dev-LoRA/resolve/main/flux1-krea-dev_rank_128-bf16.safetensors url=https://huggingface.co/PlayDustinDB/FLUX.1-Krea-dev-LoRA/resolve/main/flux1-krea-dev_rank_128-bf16.safetensors
2025-08-29T02:21:16Z | INFO  | [ Redirect ] redirect_url=http://r8-huggingface-ric1.cwlota.com/ab96a6070b8d405384d06ec35c0d826ce09d7294cd69267d02a35d02fb4f13f1?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Checksum-Mode=ENABLED&X-Amz-Credential=CWNZUVKLDHXVHEZN%2F20250829%2FUS-EAST-04A%2Fs3%2Faws4_request&X-Amz-Date=20250829T022116Z&X-Amz-Expires=600&X-Amz-SignedHeaders=host&x-id=GetObject&X-Amz-Signature=b21a8e53e66b372540e319beb5d541c50106fec9db48d7413c7e4246c382d96b url=http://hermes.services.svc.cluster.local/huggingface.co/PlayDustinDB/FLUX.1-Krea-dev-LoRA/resolve/main/flux1-krea-dev_rank_128-bf16.safetensors
2025-08-29T02:21:16Z | INFO  | [ Complete ] dest=/src/weights-cache/0d403bf300e3c590 size="1.2 GB" total_elapsed=0.738s url=https://huggingface.co/PlayDustinDB/FLUX.1-Krea-dev-LoRA/resolve/main/flux1-krea-dev_rank_128-bf16.safetensors
Downloaded weights in 0.84s
Loaded LoRAs in 4.88s
Using seed: 61958
Prompt: a pair of GB2045G eyeglasses wore by a young Japanese woman, summer vibe, realistic, studio style
[!] txt2img mode
  0%|          | 0/35 [00:00<?, ?it/s]
  3%|▎         | 1/35 [00:00<00:10,  3.35it/s]
  6%|▌         | 2/35 [00:00<00:08,  3.67it/s]
  9%|▊         | 3/35 [00:00<00:09,  3.52it/s]
 11%|█▏        | 4/35 [00:01<00:08,  3.45it/s]
 14%|█▍        | 5/35 [00:01<00:08,  3.41it/s]
 17%|█▋        | 6/35 [00:01<00:08,  3.39it/s]
 20%|██        | 7/35 [00:02<00:08,  3.38it/s]
 23%|██▎       | 8/35 [00:02<00:08,  3.37it/s]
 26%|██▌       | 9/35 [00:02<00:07,  3.37it/s]
 29%|██▊       | 10/35 [00:02<00:07,  3.37it/s]
 31%|███▏      | 11/35 [00:03<00:07,  3.36it/s]
 34%|███▍      | 12/35 [00:03<00:06,  3.36it/s]
 37%|███▋      | 13/35 [00:03<00:06,  3.36it/s]
 40%|████      | 14/35 [00:04<00:06,  3.35it/s]
 43%|████▎     | 15/35 [00:04<00:05,  3.35it/s]
 46%|████▌     | 16/35 [00:04<00:05,  3.35it/s]
 49%|████▊     | 17/35 [00:05<00:05,  3.35it/s]
 51%|█████▏    | 18/35 [00:05<00:05,  3.35it/s]
 54%|█████▍    | 19/35 [00:05<00:04,  3.35it/s]
 57%|█████▋    | 20/35 [00:05<00:04,  3.35it/s]
 60%|██████    | 21/35 [00:06<00:04,  3.35it/s]
 63%|██████▎   | 22/35 [00:06<00:03,  3.35it/s]
 66%|██████▌   | 23/35 [00:06<00:03,  3.35it/s]
 69%|██████▊   | 24/35 [00:07<00:03,  3.35it/s]
 71%|███████▏  | 25/35 [00:07<00:02,  3.35it/s]
 74%|███████▍  | 26/35 [00:07<00:02,  3.35it/s]
 77%|███████▋  | 27/35 [00:08<00:02,  3.35it/s]
 80%|████████  | 28/35 [00:08<00:02,  3.35it/s]
 83%|████████▎ | 29/35 [00:08<00:01,  3.35it/s]
 86%|████████▌ | 30/35 [00:08<00:01,  3.35it/s]
 89%|████████▊ | 31/35 [00:09<00:01,  3.35it/s]
 91%|█████████▏| 32/35 [00:09<00:00,  3.35it/s]
 94%|█████████▍| 33/35 [00:09<00:00,  3.35it/s]
 97%|█████████▋| 34/35 [00:10<00:00,  3.35it/s]
100%|██████████| 35/35 [00:10<00:00,  3.35it/s]
100%|██████████| 35/35 [00:10<00:00,  3.37it/s]
Total safe images: 1 out of 1

Version Details

Version ID: aed3e7b95fe9cad99188bb52c3ecd06d177ea9edddf04221cea284b8ad9daa41
Version Created: August 29, 2025

Run on Replicate →