codelace/forfluxmaylads 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"bespoke, 24x24 pixel grid portrait, symbolic punk style, vibrant kiwi green solid background, white/gray hair with texture starting at y=3 extending to y=17, black pupils fixed at (8,12) and (13,12), dark iris eyes with white highlights at (9,12) and (14,12), black nose dot at (11,13), gray lips spanning x=10-13 y=15-16, light skin tone with jaw defined at y=19, dark collar at bottom edge y=20-22, right-facing, pure pixel art with no gradients or anti-aliasing, clean color boundaries, all features contained within 22x22 center grid"
Output
Performance Metrics
10.10s
Prediction Time
10.57s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/Mzjbu96kECihU6wu4YwE97EzSIBDnQxCAT8ZAQa9CTrRWUwz/IMG_3589.png",
"model": "dev",
"prompt": "bespoke, 24x24 pixel grid portrait, symbolic punk style, vibrant kiwi green solid background, white/gray hair with texture starting at y=3 extending to y=17, black pupils fixed at (8,12) and (13,12), dark iris eyes with white highlights at (9,12) and (14,12), black nose dot at (11,13), gray lips spanning x=10-13 y=15-16, light skin tone with jaw defined at y=19, dark collar at bottom edge y=20-22, right-facing, pure pixel art with no gradients or anti-aliasing, clean color boundaries, all features contained within 22x22 center grid",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 3,
"output_quality": 80,
"prompt_strength": 0.8,
"extra_lora_scale": 1,
"num_inference_steps": 28
}
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
free=28631015849984 Downloading weights 2025-05-12T08:30:48Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpih1sn4wa/weights url=https://replicate.delivery/xezq/J6MxHBQrH7qcKRKgDZF1bqp2ksc2K9PZUhL6XjQQLJWgh9KF/trained_model.tar 2025-05-12T08:30:48Z | INFO | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local 2025-05-12T08:30:50Z | INFO | [ Complete ] dest=/tmp/tmpih1sn4wa/weights size="344 MB" total_elapsed=1.800s url=https://replicate.delivery/xezq/J6MxHBQrH7qcKRKgDZF1bqp2ksc2K9PZUhL6XjQQLJWgh9KF/trained_model.tar Downloaded weights in 1.82s Loaded LoRAs in 2.41s Using seed: 64793 Prompt: bespoke, 24x24 pixel grid portrait, symbolic punk style, vibrant kiwi green solid background, white/gray hair with texture starting at y=3 extending to y=17, black pupils fixed at (8,12) and (13,12), dark iris eyes with white highlights at (9,12) and (14,12), black nose dot at (11,13), gray lips spanning x=10-13 y=15-16, light skin tone with jaw defined at y=19, dark collar at bottom edge y=20-22, right-facing, pure pixel art with no gradients or anti-aliasing, clean color boundaries, all features contained within 22x22 center grid Input image size: 1038x1036 [!] Resizing input image from 1038x1036 to 1040x1040 [!] img2img mode 0%| | 0/23 [00:00<?, ?it/s] 4%|▍ | 1/23 [00:00<00:04, 4.60it/s] 9%|▊ | 2/23 [00:00<00:05, 4.02it/s] 13%|█▎ | 3/23 [00:00<00:05, 3.87it/s] 17%|█▋ | 4/23 [00:01<00:05, 3.80it/s] 22%|██▏ | 5/23 [00:01<00:04, 3.76it/s] 26%|██▌ | 6/23 [00:01<00:04, 3.74it/s] 30%|███ | 7/23 [00:01<00:04, 3.72it/s] 35%|███▍ | 8/23 [00:02<00:04, 3.72it/s] 39%|███▉ | 9/23 [00:02<00:03, 3.71it/s] 43%|████▎ | 10/23 [00:02<00:03, 3.71it/s] 48%|████▊ | 11/23 [00:02<00:03, 3.70it/s] 52%|█████▏ | 12/23 [00:03<00:02, 3.70it/s] 57%|█████▋ | 13/23 [00:03<00:02, 3.70it/s] 61%|██████ | 14/23 [00:03<00:02, 3.70it/s] 65%|██████▌ | 15/23 [00:04<00:02, 3.70it/s] 70%|██████▉ | 16/23 [00:04<00:01, 3.70it/s] 74%|███████▍ | 17/23 [00:04<00:01, 3.70it/s] 78%|███████▊ | 18/23 [00:04<00:01, 3.70it/s] 83%|████████▎ | 19/23 [00:05<00:01, 3.70it/s] 87%|████████▋ | 20/23 [00:05<00:00, 3.70it/s] 91%|█████████▏| 21/23 [00:05<00:00, 3.70it/s] 96%|█████████▌| 22/23 [00:05<00:00, 3.70it/s] 100%|██████████| 23/23 [00:06<00:00, 3.70it/s] 100%|██████████| 23/23 [00:06<00:00, 3.73it/s] Total safe images: 1 out of 1
Version Details
- Version ID
ac59085f4e6e5786c281ec931bae38710765dc2b8e385428a5c71b5df3d0565a- Version Created
- May 12, 2025