add segmind vega

CHANGELOG.md

@@ -8,6 +8,9 @@
   - **AnimateDiff** can now be used with *second pass* - enhance, upscale and hires your videos!  
   - **IP Adapter** add support for `ip-adapter-plus_sd15`, `ip-adapter-plus-face_sd15` and `ip-adapter-full-face_sd15`  
     additionally, ip-adapter can now be used in xyz-grid  
+  - [Segmind Vega](https://huggingface.co/segmind/Segmind-Vega) support  
+    - small and fast version of SDXL, only 3.1GB in size!  
+    - select from networks -> reference  
   - [Playground v1](https://huggingface.co/playgroundai/playground-v1), [Playground v2 256](https://huggingface.co/playgroundai/playground-v2-256px-base), [Playground v2 512](https://huggingface.co/playgroundai/playground-v2-512px-base), [Playground v2 1024](https://huggingface.co/playgroundai/playground-v2-1024px-aesthetic) model support  
     - simply select from *networks -> reference* and use as usual  
   - [DemoFusion](https://github.com/PRIS-CV/DemoFusion) run your SDXL generations at any resolution!  

README.md

@@ -61,8 +61,9 @@ Additional models will be added as they become available and there is public int
 - [RunwayML Stable Diffusion](https://github.com/Stability-AI/stablediffusion/) 1.x and 2.x *(all variants)*  
 - [StabilityAI Stable Diffusion XL](https://github.com/Stability-AI/generative-models)  
 - [StabilityAI Stable Video Diffusion](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid) Base and XT  
-- [Segmind SSD-1B](https://huggingface.co/segmind/SSD-1B)  
 - [LCM: Latent Consistency Models](https://github.com/openai/consistency_models)  
+- [Segmind Vega](https://huggingface.co/segmind/Segmind-Vega)  
+- [Segmind SSD-1B](https://huggingface.co/segmind/SSD-1B)  
 - [Kandinsky](https://github.com/ai-forever/Kandinsky-2) *2.1 and 2.2 and latest 3.0*  
 - [PixArt-α XL 2](https://github.com/PixArt-alpha/PixArt-alpha) *Medium and Large*  
 - [Warp Wuerstchen](https://huggingface.co/blog/wuertschen)  

html/reference.json

@@ -34,6 +34,11 @@
     "desc": "(SVD) Image-to-Video is a latent diffusion model trained to generate short video clips from an image conditioning. This model was trained to generate 25 frames at resolution 576x1024 given a context frame of the same size, finetuned from SVD Image-to-Video [14 frames]. We also finetune the widely used f8-decoder for temporal consistency.",
     "preview": "stabilityai--stable-video-diffusion-img2vid-xt.jpg"
   },
+  "Segmind Vega": {
+    "path": "segmind/Segmind-Vega",
+    "desc": "The Segmind-Vega Model is a distilled version of the Stable Diffusion XL (SDXL), offering a remarkable 70% reduction in size and an impressive 100% speedup while retaining high-quality text-to-image generation capabilities. Trained on diverse datasets, including Grit and Midjourney scrape data, it excels at creating a wide range of visual content based on textual prompts. Employing a knowledge distillation strategy, Segmind-Vega leverages the teachings of several expert models, including SDXL, ZavyChromaXL, and JuggernautXL, to combine their strengths and produce compelling visual outputs.",
+    "preview": "segmind--Segmind-Vega.jpg"
+  },
   "Segmind SSD-1B": {
     "path": "segmind/SSD-1B",
     "desc": "The Segmind Stable Diffusion Model (SSD-1B) offers a compact, efficient, and distilled version of the SDXL model. At 50% smaller and 60% faster than Stable Diffusion XL (SDXL), it provides quick and seamless performance without sacrificing image quality.",

modules/images.py

@@ -657,7 +657,8 @@ def save_video_atomic(images, filename, video_type: str = 'none', duration: floa
         for i in range(len(video_frames)):
             img = cv2.cvtColor(video_frames[i], cv2.COLOR_RGB2BGR)
             video_writer.write(img)
-        shared.log.info(f'Save video: file="{filename}" frames={len(frames)} duration={duration} fourcc={fourcc}')
+        size = os.path.getsize(filename)
+        shared.log.info(f'Save video: file="{filename}" frames={len(frames)} duration={duration} fourcc={fourcc} size={size}')
     if video_type.lower() == 'gif' or video_type.lower() == 'png':
         append = images.copy()
         image = append.pop(0)
@@ -672,7 +673,8 @@ def save_video_atomic(images, filename, video_type: str = 'none', duration: floa
             duration = 1000.0 * duration / frames,
             loop = 0 if loop else 1,
         )
-        shared.log.info(f'Save video: file="{filename}" frames={len(append) + 1} duration={duration} loop={loop}')
+        size = os.path.getsize(filename)
+        shared.log.info(f'Save video: file="{filename}" frames={len(append) + 1} duration={duration} loop={loop} size={size}')
 
 
 def save_video(p, images, filename = None, video_type: str = 'none', duration: float = 2.0, loop: bool = False, interpolate: int = 0, scale: float = 1.0, pad: int = 1, change: float = 0.3):

modules/sd_models.py

@@ -634,6 +634,10 @@ def detect_pipeline(f: str, op: str = 'model', warning=True):
                 if shared.backend == shared.Backend.ORIGINAL:
                     warn(f'Model detected as SD XL instruct pix2pix model, but attempting to load using backend=original: {op}={f} size={size} MB')
                 guess = 'Stable Diffusion XL Instruct'
+            elif size > 3138 and size < 3142: #3140
+                if shared.backend == shared.Backend.ORIGINAL:
+                    warn(f'Model detected as Segmind Vega model, but attempting to load using backend=original: {op}={f} size={size} MB')
+                guess = 'Stable Diffusion XL'
             else:
                 guess = 'Stable Diffusion'
             # guess by name

modules/ui_tempdir.py

@@ -68,7 +68,8 @@ def pil_to_temp_file(self, img: Image, dir: str, format="png") -> str: # pylint:
     with tempfile.NamedTemporaryFile(delete=False, suffix=".png", dir=dir) as tmp:
         name = tmp.name
         img.save(name, pnginfo=(metadata if use_metadata else None))
-        shared.log.debug(f'Saving temp: image="{name}"')
+        size = os.path.getsize(name)
+        shared.log.debug(f'Saving temp: image="{name}" resolution={img.width}x{img.height} size={size}')
     params = ', '.join([f'{k}: {v}' for k, v in img.info.items()])
     params = params[12:] if params.startswith('parameters: ') else params
     with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file: