baaivision/emu3-gen 📝🔢 → 🖼️

▶️ 102 runs 📅 Sep 2024 ⚙️ Cog 0.9.23 🔗 GitHub 📄 Paper ⚖️ License
text-to-image

About

Emu3-Gen for image generation

Example Output

Prompt:

"a portrait of an astronaut riding a unicorn."

Output

Example output

Performance Metrics

547.39s Prediction Time
630.23s Total Time
All Input Parameters 
{
  "prompt": "a portrait of an astronaut riding a unicorn.",
  "guidance_scale": 3,
  "negative_prompt": "lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry.",
  "positive_prompt": "masterpiece, film grained, best quality."
}
Input Parameters
prompt Type: stringDefault: a portrait of young girl.
Input prompt
guidance_scale Type: numberDefault: 3Range: 1 - 20
Scale for classifier-free guidance
negative_prompt Type: stringDefault: lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry.
Specify things to not see in the output
positive_prompt Type: stringDefault: masterpiece, film grained, best quality.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
The `seen_tokens` attribute is deprecated and will be removed in v4.41. Use the `cache_position` model input instead.
3
['<|extra_203|>a portrait of an astronaut riding a unicorn. masterpiece, film grained, best quality.', <PIL.Image.Image image mode=RGB size=720x720 at 0x7FD3B090F9D0>, '<|extra_204|>']
Version Details
Version ID
f65f4d8e2625bc9261768c129ec143c26c51f1aa11e12f2276a92fbfdf2359cd
Version Created
September 29, 2024
Run on Replicate →