jan890/flux_dev_ascii_art 🖼️🔢❓📝✓ → 🖼️
About
This AI ASCII Image Generator converts text prompts into detailed ASCII art images. Just include the trigger word "ASCII" in your text prompt, and the model, fine-tuned on Flux1 Dev, will generate an ASCII art representation of your description. The model
Example Output
Prompt:
"This image is an ASCII art representation of a human skull. The skull is rendered using a grid of ASCII characters, with the darker areas represented by more complex characters like backslashes and forward slashes, and the lighter areas represented by simpler characters like periods. The skull is set against a dark background, which enhances the contrast and gives the image a bold, striking appearance. The overall effect is a stylized, pixelated representation of a human skull that is reminiscent of early computer graphics or digital art."
Output
Performance Metrics
38.63s
Prediction Time
38.63s
Total Time
All Input Parameters
{
"model": "dev",
"prompt": "This image is an ASCII art representation of a human skull. The skull is rendered using a grid of ASCII characters, with the darker areas represented by more complex characters like backslashes and forward slashes, and the lighter areas represented by simpler characters like periods. The skull is set against a dark background, which enhances the contrast and gives the image a bold, striking appearance. The overall effect is a stylized, pixelated representation of a human skull that is reminiscent of early computer graphics or digital art.",
"lora_scale": 1,
"num_outputs": 4,
"aspect_ratio": "1:1",
"output_format": "webp",
"guidance_scale": 3.5,
"output_quality": 80,
"extra_lora_scale": 0.8,
"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: 60090 Prompt: This image is an ASCII art representation of a human skull. The skull is rendered using a grid of ASCII characters, with the darker areas represented by more complex characters like backslashes and forward slashes, and the lighter areas represented by simpler characters like periods. The skull is set against a dark background, which enhances the contrast and gives the image a bold, striking appearance. The overall effect is a stylized, pixelated representation of a human skull that is reminiscent of early computer graphics or digital art. txt2img mode Using dev model Loaded LoRAs in 8.93s The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['appearance. the overall effect is a stylized, pixelated representation of a human skull that is reminiscent of early computer graphics or digital art.', 'appearance. the overall effect is a stylized, pixelated representation of a human skull that is reminiscent of early computer graphics or digital art.', 'appearance. the overall effect is a stylized, pixelated representation of a human skull that is reminiscent of early computer graphics or digital art.', 'appearance. the overall effect is a stylized, pixelated representation of a human skull that is reminiscent of early computer graphics or digital art.'] 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:01<00:27, 1.01s/it] 7%|▋ | 2/28 [00:01<00:23, 1.13it/s] 11%|█ | 3/28 [00:02<00:23, 1.06it/s] 14%|█▍ | 4/28 [00:03<00:23, 1.03it/s] 18%|█▊ | 5/28 [00:04<00:22, 1.01it/s] 21%|██▏ | 6/28 [00:05<00:21, 1.00it/s] 25%|██▌ | 7/28 [00:06<00:21, 1.00s/it] 29%|██▊ | 8/28 [00:07<00:20, 1.01s/it] 32%|███▏ | 9/28 [00:08<00:19, 1.01s/it] 36%|███▌ | 10/28 [00:09<00:18, 1.01s/it] 39%|███▉ | 11/28 [00:10<00:17, 1.02s/it] 43%|████▎ | 12/28 [00:11<00:16, 1.02s/it] 46%|████▋ | 13/28 [00:13<00:15, 1.02s/it] 50%|█████ | 14/28 [00:14<00:14, 1.02s/it] 54%|█████▎ | 15/28 [00:15<00:13, 1.02s/it] 57%|█████▋ | 16/28 [00:16<00:12, 1.02s/it] 61%|██████ | 17/28 [00:17<00:11, 1.02s/it] 64%|██████▍ | 18/28 [00:18<00:10, 1.02s/it] 68%|██████▊ | 19/28 [00:19<00:09, 1.02s/it] 71%|███████▏ | 20/28 [00:20<00:08, 1.02s/it] 75%|███████▌ | 21/28 [00:21<00:07, 1.02s/it] 79%|███████▊ | 22/28 [00:22<00:06, 1.02s/it] 82%|████████▏ | 23/28 [00:23<00:05, 1.02s/it] 86%|████████▌ | 24/28 [00:24<00:04, 1.02s/it] 89%|████████▉ | 25/28 [00:25<00:03, 1.02s/it] 93%|█████████▎| 26/28 [00:26<00:02, 1.02s/it] 96%|█████████▋| 27/28 [00:27<00:01, 1.02s/it] 100%|██████████| 28/28 [00:28<00:00, 1.02s/it] 100%|██████████| 28/28 [00:28<00:00, 1.01s/it] Potential NSFW content was detected in one or more images. A black image will be returned instead. Try again with a different prompt and/or seed. NSFW content detected in image 0
Version Details
- Version ID
cfe93c58c8e1801be0c9b4f18627df12cd944c276cb98c2649ec7b5d4ea175f0- Version Created
- September 1, 2024