Nymbo commited on
Commit
948d89f
·
verified ·
1 Parent(s): 0c8e311

adding all kokoro voices to MCP context, plus adds links to browse all image gen and viceo gen models available

Browse files
Files changed (1) hide show
  1. app.py +17 -7
app.py CHANGED
@@ -1773,9 +1773,9 @@ kokoro_interface = gr.Interface(
1773
  ),
1774
  api_description=(
1775
  "Synthesize speech from text using Kokoro-82M TTS model. Returns (sample_rate, waveform) suitable for playback. "
1776
- "Supports unlimited text length by processing all segments. Voice examples: 'af_heart' (US female), 'am_onyx' (US male), "
1777
- "'bf_emma' (British female), 'af_sky' (US female), 'af_nicole' (US female), "
1778
- "Parameters: text (str), speed (float 0.5–2.0, default 1.25x), voice (str from 54 available options, default 'af_heart'). "
1779
  "Return the generated media to the user in this format `![Alt text](URL)`"
1780
  ),
1781
  flagging_mode="never",
@@ -1984,7 +1984,12 @@ image_generation_interface = gr.Interface(
1984
  fn=Generate_Image,
1985
  inputs=[
1986
  gr.Textbox(label="Prompt", placeholder="Enter a prompt", lines=2),
1987
- gr.Textbox(label="Model", value="black-forest-labs/FLUX.1-Krea-dev", placeholder="creator/model-name"),
 
 
 
 
 
1988
  gr.Textbox(
1989
  label="Negative Prompt",
1990
  value=(
@@ -2189,7 +2194,12 @@ video_generation_interface = gr.Interface(
2189
  fn=Generate_Video,
2190
  inputs=[
2191
  gr.Textbox(label="Prompt", placeholder="Enter a prompt for the video", lines=2),
2192
- gr.Textbox(label="Model", value="Wan-AI/Wan2.2-T2V-A14B", placeholder="creator/model-name"),
 
 
 
 
 
2193
  gr.Textbox(label="Negative Prompt", value="", lines=2),
2194
  gr.Slider(minimum=1, maximum=100, value=25, step=1, label="Steps"),
2195
  gr.Slider(minimum=1.0, maximum=20.0, value=3.5, step=0.1, label="CFG Scale"),
@@ -2202,8 +2212,8 @@ video_generation_interface = gr.Interface(
2202
  outputs=gr.Video(label="Generated Video", show_download_button=True, format="mp4"),
2203
  title="Generate Video",
2204
  description=(
2205
- "<div style=\"text-align:center\">Generate short videos via Hugging Face serverless inference. "
2206
- "Default model is Wan2.2-T2V-A14B.</div>"
2207
  ),
2208
  api_description=(
2209
  "Generate a short video from a text prompt using a Hugging Face model via serverless inference. "
 
1773
  ),
1774
  api_description=(
1775
  "Synthesize speech from text using Kokoro-82M TTS model. Returns (sample_rate, waveform) suitable for playback. "
1776
+ "Parameters: text (str), speed (float 0.5–2.0, default 1.25x), voice (str, default 'af_heart'). "
1777
+ "Voice Legend: af=American female, am=American male, bf=British female, bm=British male, ef=European female, em=European male, hf=Hindi female, hm=Hindi male, if=Italian female, im=Italian male, jf=Japanese female, jm=Japanese male, pf=Portuguese female, pm=Portuguese male, zf=Chinese female, zm=Chinese male, ff=French female. "
1778
+ "All Voices: af_alloy, af_aoede, af_bella, af_heart, af_jessica, af_kore, af_nicole, af_nova, af_river, af_sarah, af_sky, am_adam, am_echo, am_eric, am_fenrir, am_liam, am_michael, am_onyx, am_puck, am_santa, bf_alice, bf_emma, bf_isabella, bf_lily, bm_daniel, bm_fable, bm_george, bm_lewis, ef_dora, em_alex, em_santa, ff_siwis, hf_alpha, hf_beta, hm_omega, hm_psi, if_sara, im_nicola, jf_alpha, jf_gongitsune, jf_nezumi, jf_tebukuro, jm_kumo, pf_dora, pm_alex, pm_santa, zf_xiaobei, zf_xiaoni, zf_xiaoxiao, zf_xiaoyi, zm_yunjian, zm_yunxi, zm_yunxia, zm_yunyang. "
1779
  "Return the generated media to the user in this format `![Alt text](URL)`"
1780
  ),
1781
  flagging_mode="never",
 
1984
  fn=Generate_Image,
1985
  inputs=[
1986
  gr.Textbox(label="Prompt", placeholder="Enter a prompt", lines=2),
1987
+ gr.Textbox(
1988
+ label="Model",
1989
+ value="black-forest-labs/FLUX.1-Krea-dev",
1990
+ placeholder="creator/model-name",
1991
+ info="<a href=\"https://huggingface.co/models?pipeline_tag=text-to-image&inference_provider=nebius,cerebras,novita,fireworks-ai,together,fal-ai,groq,featherless-ai,nscale,hyperbolic,sambanova,cohere,replicate,scaleway,publicai,hf-inference&sort=trending\" target=\"_blank\" rel=\"noopener noreferrer\">Browse models</a>",
1992
+ ),
1993
  gr.Textbox(
1994
  label="Negative Prompt",
1995
  value=(
 
2194
  fn=Generate_Video,
2195
  inputs=[
2196
  gr.Textbox(label="Prompt", placeholder="Enter a prompt for the video", lines=2),
2197
+ gr.Textbox(
2198
+ label="Model",
2199
+ value="Wan-AI/Wan2.2-T2V-A14B",
2200
+ placeholder="creator/model-name",
2201
+ info="<a href=\"https://huggingface.co/models?pipeline_tag=text-to-video&inference_provider=nebius,cerebras,novita,fireworks-ai,together,fal-ai,groq,featherless-ai,nscale,hyperbolic,sambanova,cohere,replicate,scaleway,publicai,hf-inference&sort=trending\" target=\"_blank\" rel=\"noopener noreferrer\">Browse models</a>",
2202
+ ),
2203
  gr.Textbox(label="Negative Prompt", value="", lines=2),
2204
  gr.Slider(minimum=1, maximum=100, value=25, step=1, label="Steps"),
2205
  gr.Slider(minimum=1.0, maximum=20.0, value=3.5, step=0.1, label="CFG Scale"),
 
2212
  outputs=gr.Video(label="Generated Video", show_download_button=True, format="mp4"),
2213
  title="Generate Video",
2214
  description=(
2215
+ "<div style=\"text-align:center\">Generate short videos via Hugging Face serverless inference. "
2216
+ "Default model is Wan2.2-T2V-A14B.</div>"
2217
  ),
2218
  api_description=(
2219
  "Generate a short video from a text prompt using a Hugging Face model via serverless inference. "