alekseycalvin/acsoonr_flux 🖼️🔢❓📝✓ → 🖼️
About
ACS token
Example Output
Prompt:
"photo of acs person with green eyes and brown hair, full height, realistic hands, strolling alone through Revolutionary Soviet Petrograd in 1920 during the winter, photorealistic analog film photography, lifelike ACS person features, photorealistic textured skin and clothing details, best quality dslr mirrorless camera professional photography, extremely detailed intricate historically-accurate background, indistinguishable from life, accurate anatomy, accurate fingers"
Output
Performance Metrics
20.36s
Prediction Time
170.09s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "photo of acs person with green eyes and brown hair, full height, realistic hands, strolling alone through Revolutionary Soviet Petrograd in 1920 during the winter, photorealistic analog film photography, lifelike ACS person features, photorealistic textured skin and clothing details, best quality dslr mirrorless camera professional photography, extremely detailed intricate historically-accurate background, indistinguishable from life, accurate anatomy, accurate fingers",
"lora_scale": 1,
"num_outputs": 1,
"aspect_ratio": "16:9",
"output_format": "webp",
"guidance_scale": 4.5,
"output_quality": 100,
"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: 50401 Prompt: photo of acs person with green eyes and brown hair, full height, realistic hands, strolling alone through Revolutionary Soviet Petrograd in 1920 during the winter, photorealistic analog film photography, lifelike ACS person features, photorealistic textured skin and clothing details, best quality dslr mirrorless camera professional photography, extremely detailed intricate historically-accurate background, indistinguishable from life, accurate anatomy, accurate fingers txt2img mode Using dev model Loading LoRA weights Ensuring enough disk space... Free disk space: 9592033103872 Downloading weights 2024-08-18T12:23:57Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/9ddbe3aab1e62bfa url=https://replicate.delivery/yhqm/qxdssHbNcibvPxpxAfAobaQNC3W30qL8ogUiRMjn3gCtX4pJA/trained_model.tar 2024-08-18T12:23:59Z | INFO | [ Complete ] dest=/src/weights-cache/9ddbe3aab1e62bfa size="172 MB" total_elapsed=1.565s url=https://replicate.delivery/yhqm/qxdssHbNcibvPxpxAfAobaQNC3W30qL8ogUiRMjn3gCtX4pJA/trained_model.tar b'' Downloaded weights in 1.5929653644561768 seconds LoRA weights loaded successfully Token indices sequence length is longer than the specified maximum sequence length for this model (85 > 77). Running this sequence through the model will result in indexing errors The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['from life, accurate anatomy, accurate fingers'] 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:00<00:09, 2.97it/s] 7%|▋ | 2/28 [00:00<00:06, 3.81it/s] 11%|█ | 3/28 [00:00<00:06, 3.76it/s] 14%|█▍ | 4/28 [00:01<00:06, 3.72it/s] 18%|█▊ | 5/28 [00:01<00:06, 3.70it/s] 21%|██▏ | 6/28 [00:01<00:05, 3.70it/s] 25%|██▌ | 7/28 [00:01<00:05, 3.69it/s] 29%|██▊ | 8/28 [00:02<00:05, 3.69it/s] 32%|███▏ | 9/28 [00:02<00:05, 3.68it/s] 36%|███▌ | 10/28 [00:02<00:04, 3.69it/s] 39%|███▉ | 11/28 [00:02<00:04, 3.69it/s] 43%|████▎ | 12/28 [00:03<00:04, 3.69it/s] 46%|████▋ | 13/28 [00:03<00:04, 3.68it/s] 50%|█████ | 14/28 [00:03<00:03, 3.69it/s] 54%|█████▎ | 15/28 [00:04<00:03, 3.69it/s] 57%|█████▋ | 16/28 [00:04<00:03, 3.69it/s] 61%|██████ | 17/28 [00:04<00:02, 3.68it/s] 64%|██████▍ | 18/28 [00:04<00:02, 3.69it/s] 68%|██████▊ | 19/28 [00:05<00:02, 3.69it/s] 71%|███████▏ | 20/28 [00:05<00:02, 3.69it/s] 75%|███████▌ | 21/28 [00:05<00:01, 3.68it/s] 79%|███████▊ | 22/28 [00:05<00:01, 3.68it/s] 82%|████████▏ | 23/28 [00:06<00:01, 3.68it/s] 86%|████████▌ | 24/28 [00:06<00:01, 3.68it/s] 89%|████████▉ | 25/28 [00:06<00:00, 3.68it/s] 93%|█████████▎| 26/28 [00:07<00:00, 3.68it/s] 96%|█████████▋| 27/28 [00:07<00:00, 3.69it/s] 100%|██████████| 28/28 [00:07<00:00, 3.68it/s] 100%|██████████| 28/28 [00:07<00:00, 3.68it/s]
Version Details
- Version ID
fd7de6f580fea2cf6af655ed1e376855ce5a6d5e9fa18b2c1bd0bdf3dfb05cdc- Version Created
- August 18, 2024