Update README.md
Browse files
README.md
CHANGED
|
@@ -66,7 +66,7 @@ base_model:
|
|
| 66 |
|
| 67 |
| Component | Description |
|
| 68 |
|---|---|
|
| 69 |
-
| **Imagine** | Text-to-image generation with 90+ style LoRAs across 3 model tiers (Z-Image Turbo, Klein
|
| 70 |
| **Animate** | Image-to-video and text-to-video via LTX 2.3. 5 workflow modes: standard I2V/T2V, Best 3-stage, first-last-frame, audio-conditioned. |
|
| 71 |
| **Retouch** | Full image editor — inpainting, upscaling, reframing, face swap (InsightFace + FaceFusion), background removal, LUT color grading, optical realism effects, multi-reference compositing, and smart selection (SAM). |
|
| 72 |
| **Retexture** | Apply any of 90+ preset styles to existing images via LoRA, or transfer the style of a reference image using depth-conditioned generation. |
|
|
@@ -110,7 +110,7 @@ base_model:
|
|
| 110 |
Retouch, and Storyboard with `@mentions`.
|
| 111 |
- **Smart VRAM management** — Models load and unload sequentially to fit within 16GB. One active model at a time,
|
| 112 |
no manual memory management needed.
|
| 113 |
-
- **Multilingual UI** — English, Italian, Spanish, French, German.
|
| 114 |
- **Local LLM + VLM** — Qwen3.5-4B handles prompt enhancement, image captioning, and storyboard agents. Falls back
|
| 115 |
to Llama 3.2 3B on CPU if needed. No external API calls.
|
| 116 |
- **Optical realism** — Client-side film emulation: grain, halation, vignette, pro-mist, chromatic aberration,
|
|
|
|
| 66 |
|
| 67 |
| Component | Description |
|
| 68 |
|---|---|
|
| 69 |
+
| **Imagine** | Text-to-image generation with 90+ style LoRAs across 3 model tiers (Z-Image Turbo, Klein 9B). Character `@mentions` for consistent subjects. |
|
| 70 |
| **Animate** | Image-to-video and text-to-video via LTX 2.3. 5 workflow modes: standard I2V/T2V, Best 3-stage, first-last-frame, audio-conditioned. |
|
| 71 |
| **Retouch** | Full image editor — inpainting, upscaling, reframing, face swap (InsightFace + FaceFusion), background removal, LUT color grading, optical realism effects, multi-reference compositing, and smart selection (SAM). |
|
| 72 |
| **Retexture** | Apply any of 90+ preset styles to existing images via LoRA, or transfer the style of a reference image using depth-conditioned generation. |
|
|
|
|
| 110 |
Retouch, and Storyboard with `@mentions`.
|
| 111 |
- **Smart VRAM management** — Models load and unload sequentially to fit within 16GB. One active model at a time,
|
| 112 |
no manual memory management needed.
|
| 113 |
+
- **Multilingual UI** — English, Italian, Spanish, French, German. (COMING SOON)
|
| 114 |
- **Local LLM + VLM** — Qwen3.5-4B handles prompt enhancement, image captioning, and storyboard agents. Falls back
|
| 115 |
to Llama 3.2 3B on CPU if needed. No external API calls.
|
| 116 |
- **Optical realism** — Client-side film emulation: grain, halation, vignette, pro-mist, chromatic aberration,
|