feature: pixel party xl v1.0 model release

README.md

@@ -0,0 +1,65 @@
+---
+license: creativeml-openrail-m
+tags:
+  - text-to-image
+  - stable-diffusion
+  - diffusers
+base_model: stabilityai/stable-diffusion-xl-base-1.0
+instance_prompt: . in pixel art style
+widget:
+  - text: cute dragon. in pixel art style
+---
+
+# Pixel Party XL
+
+This is a full model training for better pixel art adherence based on SDXL. Feel free to use this model for your own projects, but please do not host it.
+
+![examples](images/examples.gif)
+
+We are building on tools for indie game development and currently have tools:
+
+- Map tiles
+- Movement animations
+- Attack animations
+- Inpainting
+- Character reshaping
+- Animation interpolation
+
+And have much more planned! :D
+
+If you want to support us or check out our other pixel art models, you can find us here [PixelLab](https://www.pixellab.ai) or on [Discord](https://discord.gg/pBeyTBF8T7).
+
+## How to use
+
+- Append ". in pixel art style" to your prompt. E.g. "cute dragon. in pixel art style"
+- Downsize the image 8x using nearest neighbor
+- Init images are very helpful
+- Model works best at around 128x128 canvas size but still excels at creating smaller items/characters/other
+- Use a VAE with fixed fp16 support: https://huggingface.co/madebyollin/sdxl-vae-fp16-fix
+- Do not use refiner
+
+### Diffusers
+
+```python
+from diffusers import DiffusionPipeline, UNet2DConditionModel
+import torch
+
+pipe = DiffusionPipeline.from_pretrained(
+    "stabilityai/stable-diffusion-xl-base-1.0",
+    torch_dtype=torch.float16,
+    unet=UNet2DConditionModel.from_pretrained("pixel-party-v1.0", torch_dtype=torch.float16),
+    use_safetensors=True,
+    variant="fp16",
+)
+pipe.to("cuda")
+
+torch.manual_seed(11215)
+prompt = "cute dragon. in pixel art style"
+negative_prompt = "mixels. amateur. multiple"
+
+image = pipe(prompt, negative_prompt=negative_prompt, num_inference_steps=25).images[0]
+```
+
+## License
+
+Please do not host this model. It is otherwise licensed under CreativeML-OpenRail-M.

config.json

@@ -0,0 +1,54 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.19.3",
+  "_name_or_path": "pixel-party-xl-v1.0/denoiser/unet",
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [5, 10, 20],
+  "block_out_channels": [320, 640, 1280],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 2048,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-5,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": 2816,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "sample_size": 128,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": [1, 2, 10],
+  "up_block_types": ["CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "UpBlock2D"],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ada8d88a0a7fe5417d4d63ee4a66897383ec682c1cd54f083acbfd47a57e7779
+size 5135149760