Upload v2.0__hunyuan/README.md with huggingface_hub

v2.0__hunyuan/README.md

@@ -0,0 +1,152 @@
+---
+language:
+- en
+tags:
+- art
+---
+
+# Flat Color - Style
+
+**Creator**: [motimalu](https://civitai.com/user/motimalu)
+**Type**: LORA
+**Base Model**: Hunyuan Video
+**Version**: v2.0 [hunyuan]
+**Trigger Words**: `flat color, no lineart`
+
+**Civitai Model ID**: 1132089
+**Civitai Version ID**: 1315010
+
+**Stats (at time of fetch)**:
+*   Downloads: 4130
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+Flat Color
+-
+Style
+Trained on images without visible lineart, flat colors, and
+little to no indication of depth.
+ℹ️ LoRA work best when applied to the base models on which they are trained.
+Please read the
+About This Version
+on the appropriate base models
+and workflow/training information.
+This is a small style LoRA I thought would be interesting to try with a v-pred model (noobai v-pred), for the reduced color bleeding and strong blacks in particular.
+The effect is quite nice and easy to evaluate in training, so I've extended the dataset with videos in following versions for text-to-video models like Wan and Hunyuan, and it is what I am generally using to test LoRA training on new models now.
+Recommended prompt structure:
+Positive prompt:
+flat color, no lineart, blending, negative space,
+{{tags}}
+masterpiece, best quality, very aesthetic, newest
+
+## Version Notes (v2.0 [hunyuan])
+
+Trained with
+https://github.com/tdrussell/diffusion-pipe
+Training data consists of:
+42 images as a combination of
+Images used from other versions this model card
+Images extracted as keyframes from several videos
+19 short video clips ~40 frames each
+Training configs:
+dataset.toml
+# Aspect ratio bucketing settings
+enable_ar_bucket = true
+min_ar = 0.5
+max_ar = 2.0
+num_ar_buckets = 7
+
+[[directory]] # IMAGES
+# Path to the directory containing images and their corresponding caption files.
+path = '/mnt/d/huanvideo/training_data/images'
+num_repeats = 5
+resolutions = [1024]
+frame_buckets = [1] # Use 1 frame for images.
+
+
+[[directory]] # VIDEOS
+# Path to the directory containing videos and their corresponding caption files.
+path = '/mnt/d/huanvideo/training_data/videos'
+num_repeats = 5
+resolutions = [256] # Set video resolution to 256 (e.g., 244p).
+frame_buckets = [33, 49, 81] # Define frame buckets for videos.
+config.toml
+# Dataset config file.
+output_dir = '/mnt/d/huanvideo/training_output'
+dataset = 'dataset.toml'
+
+# Training settings
+epochs = 50
+micro_batch_size_per_gpu = 1
+pipeline_stages = 1
+gradient_accumulation_steps = 4
+gradient_clipping = 1.0
+warmup_steps = 100
+
+# eval settings
+eval_every_n_epochs = 5
+eval_before_first_step = true
+eval_micro_batch_size_per_gpu = 1
+eval_gradient_accumulation_steps = 1
+
+# misc settings
+save_every_n_epochs = 15
+checkpoint_every_n_minutes = 30
+activation_checkpointing = true
+partition_method = 'parameters'
+save_dtype = 'bfloat16'
+caching_batch_size = 1
+steps_per_print = 1
+video_clip_mode = 'single_middle'
+
+[model]
+type = 'hunyuan-video'
+
+transformer_path = '/mnt/d/huanvideo/models/diffusion_models/hunyuan_video_720_cfgdistill_fp8_e4m3fn.safetensors'
+vae_path = '/mnt/d/huanvideo/models/vae/hunyuan_video_vae_bf16.safetensors'
+llm_path = '/mnt/d/huanvideo/models/llm'
+clip_path = '/mnt/d/huanvideo/models/clip'
+
+dtype = 'bfloat16'
+transformer_dtype = 'float8'
+timestep_sample_method = 'logit_normal'
+
+[adapter]
+type = 'lora'
+rank = 32
+dtype = 'bfloat16'
+
+[optimizer]
+type = 'adamw_optimi'
+lr = 5e-5
+betas = [0.9, 0.99]
+weight_decay = 0.02
+eps = 1e-8
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1132089?modelVersionId=1315010)**
+*   [View Full Model Page →](https://civitai.com/models/1132089)
+*   [View Creator Profile →](https://civitai.com/user/motimalu)
+
+---
+
+## Preview Images
+
+![Preview Image](./previews/1315010_53170144.mp4)
+
+---
+
+## File Information
+
+*   **Filename**: `hunyuan_flat_color_v2.safetensors`
+*   **Size**: 307.58 MB
+*   **Hash (AutoV2)**: `E732F98BE3`
+*   **Hash (SHA256)**: `E732F98BE3D6838E3C71A502BCBFDA7852C4B402C2446075D7EA0E0FAC3EEA33`
+