Tensor.Art
Create

Flat Color - Style

LORA
Original

Updated:

v2.0 [hunyuan]
v2.0 [Illustrious]
v2.0 [noobai-v-pred-1]
v1.0 [hunyuan]
v1.0 [Illustrious]
v1.0 [noobai-v-pred-1]

Flat Color - Style

Trained on images without visible lineart and flat colors and little to no indication of depth.

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, so I've extended the dataset in following versions, including Hunyuan Video.

Recommended prompt structure:

Positive prompt:

flat color, no lineart, blending, negative space,
{{tags}}
masterpiece, best quality, very awa, absurdres

Negative prompt:

(worst quality, low quality, sketch:1.1), error, bad anatomy, bad hands, watermark, ugly, distorted, censored, lowres, abstract, signature, bkub
The model deployment is abnormal, please re-upload/contact customer service.

Version Detail

Hunyuan Video
<p>Trained with <a target="_blank" rel="ugc" href="https://github.com/tdrussell/diffusion-pipe">https://github.com/tdrussell/diffusion-pipe</a></p><p>Training data consists of:</p><ul><li><p>42 images as a combination of</p><ul><li><p>Images used from other versions this model card</p></li><li><p>Images extracted as keyframes from several videos</p></li></ul></li><li><p>19 short video clips ~40 frames each</p></li></ul><p><strong>Training configs:</strong></p><p><strong>dataset.toml</strong></p><pre><code># 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.</code></pre><p><strong>config.toml</strong></p><pre><code># 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</code></pre>

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Related Posts