ignaciosgithub/pllava 🖼️🔢📝 → 📝

▶️ 298 runs 📅 Feb 2024 ⚙️ Cog 0.9.4
image-captioning image-to-text visual-question-answering

About

Example Output

Prompt:

"que se puede decir de esta imagen histopatologica?"

Output

Consistente con Linfoma difuso de grandes células.
Se realizaran técnicas de inmunohistqouímica para categorización.

Performance Metrics

2.71s Prediction Time
2.75s Total Time
All Input Parameters 
{
  "image": "https://replicate.delivery/pbxt/KSjaaQ4oatw4iARoNoU7orjhXpwB9m2LlOd4ifpe1gqZXWIo/img3.12.jpg",
  "top_p": 1,
  "prompt": "que se puede decir de esta imagen histopatologica?",
  "max_tokens": 1024,
  "temperature": 0.2
}
Input Parameters
image (required) Type: string
Input image
top_p Type: numberDefault: 1Range: 0 - 1
When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens
prompt (required) Type: string
Prompt to use for text generation
max_tokens Type: integerDefault: 1024Range: 0 - ∞
Maximum number of tokens to generate. A word is generally 2-3 tokens
temperature Type: numberDefault: 0.2Range: 0 - ∞
Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic
Output Schema

Output

Type: array • Items Type: string

Version Details
Version ID
a9a6955ca1532f479cd6839db016b57ba2cb12c088c28c2529614d6038fc612f
Version Created
February 25, 2024
Run on Replicate →