Spaces:
Running on Zero
Running on Zero
README: sdk 6.30.0 for gr.Server/gr.Workflow, studio description
Browse files
README.md
CHANGED
|
@@ -4,12 +4,33 @@ emoji: 🖼️
|
|
| 4 |
colorFrom: purple
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 6.
|
| 8 |
python_version: "3.12"
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
startup_duration_timeout: 1h
|
| 12 |
short_description: Text-to-image and image editing, based on MiniMax-H3
|
|
|
|
|
|
|
| 13 |
models:
|
| 14 |
- PrunaAI/P-H3-Image
|
| 15 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
colorFrom: purple
|
| 5 |
colorTo: indigo
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 6.30.0
|
| 8 |
python_version: "3.12"
|
| 9 |
app_file: app.py
|
| 10 |
pinned: false
|
| 11 |
startup_duration_timeout: 1h
|
| 12 |
short_description: Text-to-image and image editing, based on MiniMax-H3
|
| 13 |
+
tags:
|
| 14 |
+
- ml-intern
|
| 15 |
models:
|
| 16 |
- PrunaAI/P-H3-Image
|
| 17 |
---
|
| 18 |
+
|
| 19 |
+
<a href="https://hf.co/chat?mode=ml-intern"><img src="https://huggingface.co/datasets/huggingface/badges/resolve/main/built-with-ml-intern-sm.svg" alt="Built with ML Intern" /></a>
|
| 20 |
+
|
| 21 |
+
P-H3-Image on ZeroGPU (`xlarge`: a full RTX PRO 6000 Blackwell, 96 GB) — now behind two bespoke
|
| 22 |
+
surfaces modeled on [briaai/Fibo-2.0-editing](https://huggingface.co/spaces/briaai/Fibo-2.0-editing),
|
| 23 |
+
with the backend (`p_h3_image_fast.py`, prompt upsampler, warmup) unchanged:
|
| 24 |
+
|
| 25 |
+
- **`/` — Studio** (`gr.Server` API + custom UI, Pruna design, dark and light themes): Generate
|
| 26 |
+
and Edit modes with prompt upsampling, aspect-ratio and resolution controls (4 / 8 / 16 MP
|
| 27 |
+
text-to-image, 4 / 8 MP edits at the source's aspect ratio), up to 8 reference images, seed
|
| 28 |
+
control, all of the original examples, before/after split view, run history with one-click
|
| 29 |
+
restore, and the upsampled prompt after each run. Both modes call the same `_render` as the
|
| 30 |
+
classic UI did.
|
| 31 |
+
- **`/workflow` — Workflow canvas** (`gr.Workflow`): node-based generate/edit pipelines you can
|
| 32 |
+
rewire and chain — text-to-image into chained edits, or your own source image. To change the
|
| 33 |
+
starter graph, edit `workflow.json` in the repo.
|
| 34 |
+
|
| 35 |
+
The classic two-tab form UI is replaced by the studio; `sdk_version` moves to 6.30.0 for
|
| 36 |
+
`gr.Server`/`gr.Workflow`.
|