for testing

.gitattributes

@@ -33,5 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 vae/kl-f8-anime.ckpt filter=lfs diff=lfs merge=lfs -text
 vae/kl-f8-anime2.ckpt filter=lfs diff=lfs merge=lfs -text
 models/wd-1-3-penultimate-ucg-cont.ckpt filter=lfs diff=lfs merge=lfs -text
-models/wd-1-4-float32-booru-110k.ckpt filter=lfs diff=lfs merge=lfs -text
-wd-1-4-anime_e1.ckpt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,47 +1,11 @@
 ---
-language:
-- en
-tags:
-- stable-diffusion
-- text-to-image
 license: creativeml-openrail-m
-inference: false
-
 ---
 
-![image](https://user-images.githubusercontent.com/26317155/210155933-db3a5f1a-1ec3-4777-915c-6deff2841ce9.png)
-
-<sub>masterpiece, best quality, 1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck</sub>
-
-# Waifu Diffusion v1.4
-
-Waifu Diffusion is a latent text-to-image diffusion model that has been conditioned on high-quality anime images through fine-tuning.
-
-- [Waifu Diffusion 1.4 Anime Epoch 1](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/wd-1-4-anime_e1.ckpt): A test model made to properly ensure that the training setup works.
-- [Waifu Diffusion 1.4 Anime Inference Config](https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/wd-1-4-anime_e1.yaml): A file included to allow for inference with Automatic's WebUI and with the original Stable Diffusion codebase.
-
-## License
-
-This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
-The CreativeML OpenRAIL License specifies: 
-
-1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content 
-2. The authors claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
-3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
-[Please read the full license here](https://huggingface.co/spaces/CompVis/stable-diffusion-license)
-
-## Downstream Uses
-
-This model can be used for entertainment purposes and as a generative art assistant.
-
-## Team Members and Acknowledgements
-
-This project would not have been possible without the incredible work by Stability AI and NovelAI.
-
-- [Haru](https://github.com/harubaru)
-- [Salt](https://github.com/sALTaccount/)
-- [Cafe](https://twitter.com/cafeai_labs)
-
-In order to reach us, you can join our [Discord server](https://discord.gg/touhouai).
+Future repo for the Waifu Diffusion 1.4 models.
 
-[![Discord Server](https://discordapp.com/api/guilds/930499730843250783/widget.png?style=banner2)](https://discord.gg/touhouai)
+This repo will contain experimental models such as:
+- An AI image detector
+- A Img2Text Diffusion Prior
+- Finetuned VAEs
+- The actual latent diffusion model

models/wd-1-3-5_80000-fp32.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b438efac4434af4e482d20cdfcea64067f8dfec438628261d2f2aa60ffc41452
-size 4098020782

wd-1-4-anime_e1.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e8f4b2225b8ac6464e9d13d25b708349b1ca340c92dfc3575e8d5ef18f689457
-size 5160236290

wd-1-4-anime_e1.yaml

@@ -1,67 +0,0 @@
-model:
-  base_learning_rate: 1.0e-4
-  target: ldm.models.diffusion.ddpm.LatentDiffusion
-  params:
-    linear_start: 0.00085
-    linear_end: 0.0120
-    num_timesteps_cond: 1
-    log_every_t: 200
-    timesteps: 1000
-    first_stage_key: "jpg"
-    cond_stage_key: "txt"
-    image_size: 64
-    channels: 4
-    cond_stage_trainable: false
-    conditioning_key: crossattn
-    monitor: val/loss_simple_ema
-    scale_factor: 0.18215
-    use_ema: False # we set this to false because this is an inference only config
-
-    unet_config:
-      target: ldm.modules.diffusionmodules.openaimodel.UNetModel
-      params:
-        use_checkpoint: True
-        use_fp16: True
-        image_size: 32 # unused
-        in_channels: 4
-        out_channels: 4
-        model_channels: 320
-        attention_resolutions: [ 4, 2, 1 ]
-        num_res_blocks: 2
-        channel_mult: [ 1, 2, 4, 4 ]
-        num_head_channels: 64 # need to fix for flash-attn
-        use_spatial_transformer: True
-        use_linear_in_transformer: True
-        transformer_depth: 1
-        context_dim: 1024
-        legacy: False
-
-    first_stage_config:
-      target: ldm.models.autoencoder.AutoencoderKL
-      params:
-        embed_dim: 4
-        monitor: val/rec_loss
-        ddconfig:
-          #attn_type: "vanilla-xformers"
-          double_z: true
-          z_channels: 4
-          resolution: 256
-          in_channels: 3
-          out_ch: 3
-          ch: 128
-          ch_mult:
-          - 1
-          - 2
-          - 4
-          - 4
-          num_res_blocks: 2
-          attn_resolutions: []
-          dropout: 0.0
-        lossconfig:
-          target: torch.nn.Identity
-
-    cond_stage_config:
-      target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
-      params:
-        freeze: True
-        layer: "penultimate"

wd-1-4-anime_e2.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c76e0962bc60ccdc18e0dce387635b472b5a19038d637216030acbbe6eda2713
-size 5160236290