dock1100/flux-cute-3d 🖼️🔢❓📝✓ → 🖼️
About
Lora for flux for cute-3d (often referenced as corporate 3d style). Use `cute-3d, ` at the beginning of the prompt to trigger style. For best results use num_outputs = 4
Example Output
Prompt:
"cute-3d, hypercar, sportcar"
Output
Performance Metrics
11.85s
Prediction Time
11.91s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "cute-3d, hypercar, sportcar",
"lora_scale": 1,
"num_outputs": 1,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 3.5,
"output_quality": 90,
"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
Using seed: 1962 Prompt: cute-3d, hypercar, sportcar [!] txt2img mode Using dev model free=9017107644416 Downloading weights 2024-10-18T07:48:25Z | INFO | [ Initiating ] chunk_size=150M dest=/tmp/tmpjxbsh13g/weights url=https://replicate.delivery/yhqm/oJlZMBTQ4qqyP5PkWDsfsx8C3S6UU2zRbMhd44L0nWa82xzJA/trained_model.tar 2024-10-18T07:48:27Z | INFO | [ Complete ] dest=/tmp/tmpjxbsh13g/weights size="172 MB" total_elapsed=1.200s url=https://replicate.delivery/yhqm/oJlZMBTQ4qqyP5PkWDsfsx8C3S6UU2zRbMhd44L0nWa82xzJA/trained_model.tar Downloaded weights in 1.23s Loaded LoRAs in 1.86s 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:09, 2.87it/s] 7%|▋ | 2/28 [00:00<00:08, 3.20it/s] 11%|█ | 3/28 [00:00<00:08, 3.04it/s] 14%|█▍ | 4/28 [00:01<00:08, 2.97it/s] 18%|█▊ | 5/28 [00:01<00:07, 2.94it/s] 21%|██▏ | 6/28 [00:02<00:07, 2.92it/s] 25%|██▌ | 7/28 [00:02<00:07, 2.90it/s] 29%|██▊ | 8/28 [00:02<00:06, 2.89it/s] 32%|███▏ | 9/28 [00:03<00:06, 2.89it/s] 36%|███▌ | 10/28 [00:03<00:06, 2.88it/s] 39%|███▉ | 11/28 [00:03<00:05, 2.88it/s] 43%|████▎ | 12/28 [00:04<00:05, 2.88it/s] 46%|████▋ | 13/28 [00:04<00:05, 2.88it/s] 50%|█████ | 14/28 [00:04<00:04, 2.88it/s] 54%|█████▎ | 15/28 [00:05<00:04, 2.88it/s] 57%|█████▋ | 16/28 [00:05<00:04, 2.88it/s] 61%|██████ | 17/28 [00:05<00:03, 2.87it/s] 64%|██████▍ | 18/28 [00:06<00:03, 2.87it/s] 68%|██████▊ | 19/28 [00:06<00:03, 2.87it/s] 71%|███████▏ | 20/28 [00:06<00:02, 2.87it/s] 75%|███████▌ | 21/28 [00:07<00:02, 2.87it/s] 79%|███████▊ | 22/28 [00:07<00:02, 2.87it/s] 82%|████████▏ | 23/28 [00:07<00:01, 2.87it/s] 86%|████████▌ | 24/28 [00:08<00:01, 2.87it/s] 89%|████████▉ | 25/28 [00:08<00:01, 2.87it/s] 93%|█████████▎| 26/28 [00:08<00:00, 2.87it/s] 96%|█████████▋| 27/28 [00:09<00:00, 2.87it/s] 100%|██████████| 28/28 [00:09<00:00, 2.87it/s] 100%|██████████| 28/28 [00:09<00:00, 2.89it/s]
Version Details
- Version ID
abaf53bc90452c82e8c91ab7da5367aa01270cac56f36860360842ce49622a9f- Version Created
- October 17, 2024