giksant/giceli 🖼️🔢❓📝✓ → 🖼️
About
Example Output
Prompt:
"
giceli
"A professional woman with shoulder-length dark brown hair and a confident, friendly expression sits at a modern, minimalist desk. She is wearing a stylish outfit consisting of a camel-colored ribbed long-sleeve top and a deep blue sleeveless blazer. Her makeup is well-applied, with dark eyeliner, soft brown eyeshadow, and a natural pink lip color. She wears elegant gold jewelry, including hoop earrings, multiple rings, and a delicate bracelet. She is holding a small blue book with the title 'Catherine Antiansiedad,' featuring an illustration of a clock and a running person, suggesting a theme related to anxiety management.
The setting is a clean, well-organized workspace with a white marble desk. On the desk, there is a realistic anatomical brain model with red veins resting on a thick hardcover book, a pair of stylish eyeglasses, and a white ceramic cup. A small decorative tray holds gold accessories, adding a touch of elegance. The background features a modern interior with white walls, floating shelves with books, and a large black-framed window allowing natural light to enter. The overall aesthetic is warm, professional, and intellectual, suggesting themes of psychology, neuroscience, or personal development."
"Output
Performance Metrics
5.27s
Prediction Time
5.28s
Total Time
All Input Parameters
{
"image": "https://replicate.delivery/pbxt/MPFnmDwrjDemmwdgIqUiq8DQypbJ6XuhRjewaK4IVBNzOMzW/f300023d-a28f-4e65-b72b-85b8a881474b.jpg",
"model": "dev",
"prompt": "giceli \n\n\"A professional woman with shoulder-length dark brown hair and a confident, friendly expression sits at a modern, minimalist desk. She is wearing a stylish outfit consisting of a camel-colored ribbed long-sleeve top and a deep blue sleeveless blazer. Her makeup is well-applied, with dark eyeliner, soft brown eyeshadow, and a natural pink lip color. She wears elegant gold jewelry, including hoop earrings, multiple rings, and a delicate bracelet. She is holding a small blue book with the title 'Catherine Antiansiedad,' featuring an illustration of a clock and a running person, suggesting a theme related to anxiety management. \n\nThe setting is a clean, well-organized workspace with a white marble desk. On the desk, there is a realistic anatomical brain model with red veins resting on a thick hardcover book, a pair of stylish eyeglasses, and a white ceramic cup. A small decorative tray holds gold accessories, adding a touch of elegance. The background features a modern interior with white walls, floating shelves with books, and a large black-framed window allowing natural light to enter. The overall aesthetic is warm, professional, and intellectual, suggesting themes of psychology, neuroscience, or personal development.\"",
"go_fast": false,
"lora_scale": 1,
"megapixels": "1",
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "jpg",
"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
2025-01-29 13:54:12.184 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-29 13:54:12.184 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 91%|█████████▏| 278/304 [00:00<00:00, 2761.53it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2654.39it/s] 2025-01-29 13:54:12.299 | SUCCESS | fp8.lora_loading:unload_loras:564 - LoRAs unloaded in 0.12s 2025-01-29 13:54:12.300 | INFO | fp8.lora_loading:convert_lora_weights:498 - Loading LoRA weights for /src/weights-cache/ca13fb4c2903ffe1 2025-01-29 13:54:12.414 | INFO | fp8.lora_loading:convert_lora_weights:519 - LoRA weights loaded 2025-01-29 13:54:12.414 | DEBUG | fp8.lora_loading:apply_lora_to_model:574 - Extracting keys 2025-01-29 13:54:12.415 | DEBUG | fp8.lora_loading:apply_lora_to_model:581 - Keys extracted Applying LoRA: 0%| | 0/304 [00:00<?, ?it/s] Applying LoRA: 91%|█████████▏| 278/304 [00:00<00:00, 2762.78it/s] Applying LoRA: 100%|██████████| 304/304 [00:00<00:00, 2655.40it/s] 2025-01-29 13:54:12.529 | SUCCESS | fp8.lora_loading:load_lora:539 - LoRA applied in 0.23s Using seed: 41798 Image detected - setting to img2img mode Input image size: 828x1196 Input image size set to: 832x1200 0it [00:00, ?it/s] 1it [00:00, 8.90it/s] 2it [00:00, 6.19it/s] 3it [00:00, 5.63it/s] 4it [00:00, 5.39it/s] 5it [00:00, 5.24it/s] 6it [00:01, 5.13it/s] 7it [00:01, 5.10it/s] 8it [00:01, 5.07it/s] 9it [00:01, 5.06it/s] 10it [00:01, 5.05it/s] 11it [00:02, 5.04it/s] 12it [00:02, 5.04it/s] 13it [00:02, 5.04it/s] 14it [00:02, 5.05it/s] 15it [00:02, 5.04it/s] 16it [00:03, 5.04it/s] 17it [00:03, 5.08it/s] 18it [00:03, 5.06it/s] 19it [00:03, 5.05it/s] 20it [00:03, 5.05it/s] 21it [00:04, 5.08it/s] 22it [00:04, 5.08it/s] 23it [00:04, 5.07it/s] 23it [00:04, 5.15it/s] Total safe images: 1 out of 1
Version Details
- Version ID
7b133db1e96e15e999b6fe2d7554dbb559aaf8c03883757a98d9b28e639d9eef- Version Created
- January 29, 2025