Duplicate from UnifiedHorusRA/Furry_Enhancer_Video

Co-authored-by: Nekhbet Wadjet <UnifiedHorusRA@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Furry Enhancer Wan2.2 V1 High Noise I2V .safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47bbc27e3c1a449e235e756b27df36a40c986e5ab3372a2d48fdd49334f1b49
+size 613516056

README.md

@@ -0,0 +1,22 @@
+---
+language:
+- en
+tags:
+- art
+---
+# Furry Enhancer  Video
+
+**Creator**: [freek22](https://civitai.com/user/freek22)
+**Civitai Model Page**: [https://civitai.com/models/1782485](https://civitai.com/models/1782485)
+
+---
+
+This repository contains multiple versions of the 'Furry Enhancer  Video' model from Civitai.
+Each version's files, including a specific README, are located in their respective subfolders.
+
+## Versions Included in this Repository
+
+| Version Name | Folder on Hugging Face | Civitai Link |
+|--------------|------------------------|--------------|
+| WAN 2.2 T2V V1.0HighNoise | [`WAN_2.2_T2V_V1.0HighNoise`](https://huggingface.co/UnifiedHorusRA/Furry_Enhancer_Video/tree/main/WAN_2.2_T2V_V1.0HighNoise) | [Link](https://civitai.com/models/1782485?modelVersionId=2144066) |
+| WAN 2.2 T2V V1.0Low Noise | [`WAN_2.2_T2V_V1.0Low_Noise`](https://huggingface.co/UnifiedHorusRA/Furry_Enhancer_Video/tree/main/WAN_2.2_T2V_V1.0Low_Noise) | [Link](https://civitai.com/models/1782485?modelVersionId=2144527) |

WAN_2.1_T2V_V1.1/README.md

@@ -0,0 +1,107 @@
+---
+language:
+- en
+tags:
+- art
+---
+
+# Furry Enhancer  Video
+
+**Creator**: [freek22](https://civitai.com/user/freek22)
+**Type**: LORA
+**Base Model**: Wan Video 14B t2v
+**Version**: WAN 2.1 T2V V1.1
+**Trigger Words**: `N/A`
+
+**Civitai Model ID**: 1782485
+**Civitai Version ID**: 2047348
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 248
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This Lora is made to enhance the ability / quality to create anthro and furry, and creatures
+but it works also for all kind of other fantasy creatures and animals too
+the range that it can handle  for example  the Wan 2.2 V2 Lora is from comic and drawing towards real photos .
+i made the lora for Hunyuan Video , WAN 2.1 and 2.2 (SFW and NSFW)
+Furry Enhancer Hunyuan V1
+The
+Hunyuan Video
+version is trained for Text to Video (T2V) but i also tested it on Image to Video its also working with it very good but not made for that.
+All example images for the Hunyuan Video are made T2V
+Its also compatible with
+Ratatoskr Hunyuan
+Wan 2.1 I2v and T2V V1
+The Wan 2.1 has 2 different models
+I2V and T2V
+the image to video is in most cases the model of choice for Wan
+for the Text to Video Variant please read the description.
+Its also compatible
+Ratatoskr WAN 2.1 (ITV)
+and will for sure increase the quality especially in the NSFW Area.
+I also tested the I2V Lora with Wan 2.2 it seems to enhance the result too but very experimental
+Wan 2.2 I2V and T2V V1
+This enhancer version is for
+Wan 2.2
+its splitted in basically 2 Loras: low and high noise
+both loras for I2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+whats the pros of this lora compared to the wan 2.1?
+more consistent
+more specimen
+better in sfw and nsfw
+i recommend using both loras and use the workflow in the training folder Note: your resolution needed to set between 0.4 (480P) and 0.92 (720p) overwise the lora generate backscreens or other failures.
+for strength i prefer the full 1.0 strength its tested
+its tested with the original wan 2.2 model
+also in a short test with my
+Ratatoskr WAN 2.2 Hybrid v1.0 WIP
+model (use only the high noise version with that model)
+for technical data about Wan 2.2 visit there official site
+here:
+V2 Furry Enhancer High Noise
+Changes compared to V1
+more consistent
+more specimen
+better overall movements
+more stable overall
+way better with comic and anime than V1
+better in sfw and nsfw
+i recommend using the V1 Version of the
+WAN 2.2 I2V V1.0Low Noise
+Note: I used for example the old workflow for this model to compare V1 with V1 if you like the newest workflow download the training folder.
+Important for this workflow is to keep the resolution between 0.4 and 0.92 (480p - 720p)
+Making such loras take a huge amount of cost and time please support my work with a like.
+and please check out my other models and loras too ;-)
+made by
+freek22
+
+## Version Notes (WAN 2.1 T2V V1.1)
+
+First Release Version
+Note training an T2V Lora is not an easy task it did actually take a lot of epoch till it actually worked properly.
+the lora needs way more description on the image than the I2V variant if you force a specific output for example clothing it tends to make the character note when the clothing is not described ;-)
+also sometimes it fails completely but its still the first release version .
+i have tested several wan models and the output may differ a lot with the model i used for the gallery pictures WAN Fusion X to save time.
+the used workflow and settings i used for gallery can be found in the soldier cat image.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1782485?modelVersionId=2047348)**
+*   [View Full Model Page →](https://civitai.com/models/1782485)
+*   [View Creator Profile →](https://civitai.com/user/freek22)
+
+---
+
+## File Information
+
+*   **Filename**: `Furry enhancer T2VV1.1.safetensors`
+*   **Size**: 585.10 MB
+*   **Hash (AutoV2)**: `8AD26C6422`
+*   **Hash (SHA256)**: `8AD26C64226A6348BF9DAC9AD51DEDB204526B40DDAC8B28E3314CF5B44F2449`

WAN_2.2_I2V_V1.0HighNoise/Furry Enhancer Wan2.2 V1 High Noise I2V .safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a47bbc27e3c1a449e235e756b27df36a40c986e5ab3372a2d48fdd49334f1b49
+size 613516056

WAN_2.2_I2V_V1.0HighNoise/README.md

@@ -0,0 +1,111 @@
+---
+language:
+- en
+tags:
+- art
+---
+
+# Furry Enhancer  Video
+
+**Creator**: [freek22](https://civitai.com/user/freek22)
+**Type**: LORA
+**Base Model**: Wan Video 2.2 I2V-A14B
+**Version**: WAN 2.2 I2V V1.0HighNoise
+**Trigger Words**: `N/A`
+
+**Civitai Model ID**: 1782485
+**Civitai Version ID**: 2132896
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 650
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This Lora is made to enhance the ability / quality to create anthro and furry, and creatures
+but it works also for all kind of other fantasy creatures and animals too
+the range that it can handle  for example  the Wan 2.2 V2 Lora is from comic and drawing towards real photos .
+i made the lora for Hunyuan Video , WAN 2.1 and 2.2 (SFW and NSFW)
+Furry Enhancer Hunyuan V1
+The
+Hunyuan Video
+version is trained for Text to Video (T2V) but i also tested it on Image to Video its also working with it very good but not made for that.
+All example images for the Hunyuan Video are made T2V
+Its also compatible with
+Ratatoskr Hunyuan
+Wan 2.1 I2v and T2V V1
+The Wan 2.1 has 2 different models
+I2V and T2V
+the image to video is in most cases the model of choice for Wan
+for the Text to Video Variant please read the description.
+Its also compatible
+Ratatoskr WAN 2.1 (ITV)
+and will for sure increase the quality especially in the NSFW Area.
+I also tested the I2V Lora with Wan 2.2 it seems to enhance the result too but very experimental
+Wan 2.2 I2V and T2V V1
+This enhancer version is for
+Wan 2.2
+its splitted in basically 2 Loras: low and high noise
+both loras for I2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+whats the pros of this lora compared to the wan 2.1?
+more consistent
+more specimen
+better in sfw and nsfw
+i recommend using both loras and use the workflow in the training folder Note: your resolution needed to set between 0.4 (480P) and 0.92 (720p) overwise the lora generate backscreens or other failures.
+for strength i prefer the full 1.0 strength its tested
+its tested with the original wan 2.2 model
+also in a short test with my
+Ratatoskr WAN 2.2 Hybrid v1.0 WIP
+model (use only the high noise version with that model)
+for technical data about Wan 2.2 visit there official site
+here:
+V2 Furry Enhancer High Noise
+Changes compared to V1
+more consistent
+more specimen
+better overall movements
+more stable overall
+way better with comic and anime than V1
+better in sfw and nsfw
+i recommend using the V1 Version of the
+WAN 2.2 I2V V1.0Low Noise
+Note: I used for example the old workflow for this model to compare V1 with V1 if you like the newest workflow download the training folder.
+Important for this workflow is to keep the resolution between 0.4 and 0.92 (480p - 720p)
+Making such loras take a huge amount of cost and time please support my work with a like.
+and please check out my other models and loras too ;-)
+made by
+freek22
+
+## Version Notes (WAN 2.2 I2V V1.0HighNoise)
+
+High Noise Lora:
+This enhancer version is for Wan 2.2 its splitted in basically 2 Loras: low and high noise
+both loras for I2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+whats the pros of this lora compared to the wan 2.1?
+more consistent
+more specimen
+better in sfw and nsfw
+i recommend using both loras in the video metadata there is a comfy workflow for using it.
+if you like to support me please give a like and Check out my other models.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1782485?modelVersionId=2132896)**
+*   [View Full Model Page →](https://civitai.com/models/1782485)
+*   [View Creator Profile →](https://civitai.com/user/freek22)
+
+---
+
+## File Information
+
+*   **Filename**: `Furry Enhancer Wan2.2 V1 High Noise I2V .safetensors`
+*   **Size**: 585.09 MB
+*   **Hash (AutoV2)**: `A47BBC27E3`
+*   **Hash (SHA256)**: `A47BBC27E3C1A449E235E756B27DF36A40C986E5AB3372A2D48FDD49334F1B49`

WAN_2.2_I2V_V1.0Low_Noise/Furry Enhancer Wan2.2 V1 Low Noise I2V .safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c37b1e82ed84807f2dd16258d9c98af0ba12c77a7b3829581fcc2cdc6646fc4
+size 613516056

WAN_2.2_I2V_V1.0Low_Noise/README.md

@@ -0,0 +1,111 @@
+---
+language:
+- en
+tags:
+- art
+---
+
+# Furry Enhancer  Video
+
+**Creator**: [freek22](https://civitai.com/user/freek22)
+**Type**: LORA
+**Base Model**: Wan Video 2.2 I2V-A14B
+**Version**: WAN 2.2 I2V V1.0Low Noise
+**Trigger Words**: `anthro`
+
+**Civitai Model ID**: 1782485
+**Civitai Version ID**: 2132861
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 578
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This Lora is made to enhance the ability / quality to create anthro and furry, and creatures
+but it works also for all kind of other fantasy creatures and animals too
+the range that it can handle  for example  the Wan 2.2 V2 Lora is from comic and drawing towards real photos .
+i made the lora for Hunyuan Video , WAN 2.1 and 2.2 (SFW and NSFW)
+Furry Enhancer Hunyuan V1
+The
+Hunyuan Video
+version is trained for Text to Video (T2V) but i also tested it on Image to Video its also working with it very good but not made for that.
+All example images for the Hunyuan Video are made T2V
+Its also compatible with
+Ratatoskr Hunyuan
+Wan 2.1 I2v and T2V V1
+The Wan 2.1 has 2 different models
+I2V and T2V
+the image to video is in most cases the model of choice for Wan
+for the Text to Video Variant please read the description.
+Its also compatible
+Ratatoskr WAN 2.1 (ITV)
+and will for sure increase the quality especially in the NSFW Area.
+I also tested the I2V Lora with Wan 2.2 it seems to enhance the result too but very experimental
+Wan 2.2 I2V and T2V V1
+This enhancer version is for
+Wan 2.2
+its splitted in basically 2 Loras: low and high noise
+both loras for I2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+whats the pros of this lora compared to the wan 2.1?
+more consistent
+more specimen
+better in sfw and nsfw
+i recommend using both loras and use the workflow in the training folder Note: your resolution needed to set between 0.4 (480P) and 0.92 (720p) overwise the lora generate backscreens or other failures.
+for strength i prefer the full 1.0 strength its tested
+its tested with the original wan 2.2 model
+also in a short test with my
+Ratatoskr WAN 2.2 Hybrid v1.0 WIP
+model (use only the high noise version with that model)
+for technical data about Wan 2.2 visit there official site
+here:
+V2 Furry Enhancer High Noise
+Changes compared to V1
+more consistent
+more specimen
+better overall movements
+more stable overall
+way better with comic and anime than V1
+better in sfw and nsfw
+i recommend using the V1 Version of the
+WAN 2.2 I2V V1.0Low Noise
+Note: I used for example the old workflow for this model to compare V1 with V1 if you like the newest workflow download the training folder.
+Important for this workflow is to keep the resolution between 0.4 and 0.92 (480p - 720p)
+Making such loras take a huge amount of cost and time please support my work with a like.
+and please check out my other models and loras too ;-)
+made by
+freek22
+
+## Version Notes (WAN 2.2 I2V V1.0Low Noise)
+
+Low Noise Lora:
+This enhancer version is for Wan 2.2 its splitted in basically 2 Loras: low and high noise
+both loras for I2V are trained on the same dataset. I its my own dataset  before i trained  with  the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+whats the pros of this lora compared to the wan 2.1?
+more consistent
+more specimen
+better in sfw and nsfw
+i recommend using both loras in the video metadata there is a comfy workflow for using it.
+if you like to support me please give a like and Check out my other models.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1782485?modelVersionId=2132861)**
+*   [View Full Model Page →](https://civitai.com/models/1782485)
+*   [View Creator Profile →](https://civitai.com/user/freek22)
+
+---
+
+## File Information
+
+*   **Filename**: `Furry Enhancer Wan2.2 V1 Low Noise I2V .safetensors`
+*   **Size**: 585.09 MB
+*   **Hash (AutoV2)**: `1C37B1E82E`
+*   **Hash (SHA256)**: `1C37B1E82ED84807F2DD16258D9C98AF0BA12C77A7B3829581FCC2CDC6646FC4`

WAN_2.2_I2V_V2.0HighNoise/Furry Enhancer Wan2.2 V2 High Noise I2V .safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3721416feeb783aca8208703c7540d91f1f79818df236de85be91a63c7e6682
+size 613516056

WAN_2.2_I2V_V2.0HighNoise/README.md

@@ -0,0 +1,118 @@
+---
+language:
+- en
+tags:
+- art
+---
+
+# Furry Enhancer  Video
+
+**Creator**: [freek22](https://civitai.com/user/freek22)
+**Type**: LORA
+**Base Model**: Wan Video 2.2 I2V-A14B
+**Version**: WAN 2.2 I2V V2.0HighNoise
+**Trigger Words**: `anthro, furry`
+
+**Civitai Model ID**: 1782485
+**Civitai Version ID**: 2192137
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 264
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This Lora is made to enhance the ability / quality to create anthro and furry, and creatures
+but it works also for all kind of other fantasy creatures and animals too
+the range that it can handle  for example  the Wan 2.2 V2 Lora is from comic and drawing towards real photos .
+i made the lora for Hunyuan Video , WAN 2.1 and 2.2 (SFW and NSFW)
+Furry Enhancer Hunyuan V1
+The
+Hunyuan Video
+version is trained for Text to Video (T2V) but i also tested it on Image to Video its also working with it very good but not made for that.
+All example images for the Hunyuan Video are made T2V
+Its also compatible with
+Ratatoskr Hunyuan
+Wan 2.1 I2v and T2V V1
+The Wan 2.1 has 2 different models
+I2V and T2V
+the image to video is in most cases the model of choice for Wan
+for the Text to Video Variant please read the description.
+Its also compatible
+Ratatoskr WAN 2.1 (ITV)
+and will for sure increase the quality especially in the NSFW Area.
+I also tested the I2V Lora with Wan 2.2 it seems to enhance the result too but very experimental
+Wan 2.2 I2V and T2V V1
+This enhancer version is for
+Wan 2.2
+its splitted in basically 2 Loras: low and high noise
+both loras for I2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+whats the pros of this lora compared to the wan 2.1?
+more consistent
+more specimen
+better in sfw and nsfw
+i recommend using both loras and use the workflow in the training folder Note: your resolution needed to set between 0.4 (480P) and 0.92 (720p) overwise the lora generate backscreens or other failures.
+for strength i prefer the full 1.0 strength its tested
+its tested with the original wan 2.2 model
+also in a short test with my
+Ratatoskr WAN 2.2 Hybrid v1.0 WIP
+model (use only the high noise version with that model)
+for technical data about Wan 2.2 visit there official site
+here:
+V2 Furry Enhancer High Noise
+Changes compared to V1
+more consistent
+more specimen
+better overall movements
+more stable overall
+way better with comic and anime than V1
+better in sfw and nsfw
+i recommend using the V1 Version of the
+WAN 2.2 I2V V1.0Low Noise
+Note: I used for example the old workflow for this model to compare V1 with V1 if you like the newest workflow download the training folder.
+Important for this workflow is to keep the resolution between 0.4 and 0.92 (480p - 720p)
+Making such loras take a huge amount of cost and time please support my work with a like.
+and please check out my other models and loras too ;-)
+made by
+freek22
+
+## Version Notes (WAN 2.2 I2V V2.0HighNoise)
+
+High Noise Lora V2
+This enhancer version is for Wan 2.2
+its trained my own dataset
+it's completely synthetic so no real persons or art is used for the dataset.
+the biggest change in this dataset is its now completely trained on videos
+Changes compared to V1
+more consistent
+more specimen
+better overall movements
+more stable overall
+way better with comic and anime than V1
+better in sfw and nsfw
+i recommend using the V1 Version of the
+WAN 2.2 I2V V1.0Low Noise
+Note: I used for example the old workflow for this model to compare V1 with V1 if you like the newest workflow download the training folder.
+Important for this workflow is to keep the resolution between 0.4 and 0.92 (480p - 720p)
+if you like to support me please give a like and Check out my other models.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1782485?modelVersionId=2192137)**
+*   [View Full Model Page →](https://civitai.com/models/1782485)
+*   [View Creator Profile →](https://civitai.com/user/freek22)
+
+---
+
+## File Information
+
+*   **Filename**: `Furry Enhancer Wan2.2 V2 High Noise I2V .safetensors`
+*   **Size**: 585.09 MB
+*   **Hash (AutoV2)**: `D3721416FE`
+*   **Hash (SHA256)**: `D3721416FEEB783ACA8208703C7540D91F1F79818DF236DE85BE91A63C7E6682`

WAN_2.2_T2V_V1.0HighNoise/README.md

@@ -0,0 +1,117 @@
+---
+language:
+- en
+tags:
+- art
+---
+
+# Furry Enhancer  Video
+
+**Creator**: [freek22](https://civitai.com/user/freek22)
+**Type**: LORA
+**Base Model**: Wan Video 2.2 T2V-A14B
+**Version**: WAN 2.2 T2V V1.0HighNoise
+**Trigger Words**: `anthro, furry`
+
+**Civitai Model ID**: 1782485
+**Civitai Version ID**: 2144066
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 184
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This Lora is made to enhance the ability / quality to create anthro and furry, and creatures
+but it works also for all kind of other fantasy creatures and animals too
+the range that it can handle  for example  the Wan 2.2 V2 Lora is from comic and drawing towards real photos .
+i made the lora for Hunyuan Video , WAN 2.1 and 2.2 (SFW and NSFW)
+Furry Enhancer Hunyuan V1
+The
+Hunyuan Video
+version is trained for Text to Video (T2V) but i also tested it on Image to Video its also working with it very good but not made for that.
+All example images for the Hunyuan Video are made T2V
+Its also compatible with
+Ratatoskr Hunyuan
+Wan 2.1 I2v and T2V V1
+The Wan 2.1 has 2 different models
+I2V and T2V
+the image to video is in most cases the model of choice for Wan
+for the Text to Video Variant please read the description.
+Its also compatible
+Ratatoskr WAN 2.1 (ITV)
+and will for sure increase the quality especially in the NSFW Area.
+I also tested the I2V Lora with Wan 2.2 it seems to enhance the result too but very experimental
+Wan 2.2 I2V and T2V V1
+This enhancer version is for
+Wan 2.2
+its splitted in basically 2 Loras: low and high noise
+both loras for I2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+whats the pros of this lora compared to the wan 2.1?
+more consistent
+more specimen
+better in sfw and nsfw
+i recommend using both loras and use the workflow in the training folder Note: your resolution needed to set between 0.4 (480P) and 0.92 (720p) overwise the lora generate backscreens or other failures.
+for strength i prefer the full 1.0 strength its tested
+its tested with the original wan 2.2 model
+also in a short test with my
+Ratatoskr WAN 2.2 Hybrid v1.0 WIP
+model (use only the high noise version with that model)
+for technical data about Wan 2.2 visit there official site
+here:
+V2 Furry Enhancer High Noise
+Changes compared to V1
+more consistent
+more specimen
+better overall movements
+more stable overall
+way better with comic and anime than V1
+better in sfw and nsfw
+i recommend using the V1 Version of the
+WAN 2.2 I2V V1.0Low Noise
+Note: I used for example the old workflow for this model to compare V1 with V1 if you like the newest workflow download the training folder.
+Important for this workflow is to keep the resolution between 0.4 and 0.92 (480p - 720p)
+Making such loras take a huge amount of cost and time please support my work with a like.
+and please check out my other models and loras too ;-)
+made by
+freek22
+
+## Version Notes (WAN 2.2 T2V V1.0HighNoise)
+
+High Noise Model
+This enhancer version is for Wan 2.2 T2V like the I2V its made for anthro / furry and fantasy creatures sfw and nsfw
+its splitted in basically 2 Loras: low and high noise
+both loras for T2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+i recommend using both loras in the video metadata there is a comfy workflow for using it.
+for the workflow all videos contain the workflows but i also packed the workflow in the "training" zip file.
+for this workflow i can recommend a step count between 8- 10 steps
+the model is only tested with the standard model and
+wan 2.2 lightning
+the model weight in all my testings was 1.0
+More information to wan 2.2 t2v you found
+here
+Note: this is V1 of this model so it sometimes still can fail also its very "spicy" and need for example descriptions for clothing
+Important:
+training such loras is very costly so if you like to support me please give a like and Check out my other models too.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1782485?modelVersionId=2144066)**
+*   [View Full Model Page →](https://civitai.com/models/1782485)
+*   [View Creator Profile →](https://civitai.com/user/freek22)
+
+---
+
+## File Information
+
+*   **Filename**: `Furry Enhancer Wan2.2 V1 High Noise .safetensors`
+*   **Size**: 585.09 MB
+*   **Hash (AutoV2)**: `270E119887`
+*   **Hash (SHA256)**: `270E119887CBE162CD5180D965AA528D1F2C513FC5187B4CBB85787CD0441736`

WAN_2.2_T2V_V1.0Low_Noise/README.md

@@ -0,0 +1,117 @@
+---
+language:
+- en
+tags:
+- art
+---
+
+# Furry Enhancer  Video
+
+**Creator**: [freek22](https://civitai.com/user/freek22)
+**Type**: LORA
+**Base Model**: Wan Video 2.2 T2V-A14B
+**Version**: WAN 2.2 T2V V1.0Low Noise
+**Trigger Words**: `anthro, furry`
+
+**Civitai Model ID**: 1782485
+**Civitai Version ID**: 2144527
+
+**Stats (at time of fetch for this version)**:
+*   Downloads: 175
+*   Rating: 0 (0 ratings)
+*   Favorites: N/A
+
+---
+
+## 📄 Description (Parent Model)
+
+This Lora is made to enhance the ability / quality to create anthro and furry, and creatures
+but it works also for all kind of other fantasy creatures and animals too
+the range that it can handle  for example  the Wan 2.2 V2 Lora is from comic and drawing towards real photos .
+i made the lora for Hunyuan Video , WAN 2.1 and 2.2 (SFW and NSFW)
+Furry Enhancer Hunyuan V1
+The
+Hunyuan Video
+version is trained for Text to Video (T2V) but i also tested it on Image to Video its also working with it very good but not made for that.
+All example images for the Hunyuan Video are made T2V
+Its also compatible with
+Ratatoskr Hunyuan
+Wan 2.1 I2v and T2V V1
+The Wan 2.1 has 2 different models
+I2V and T2V
+the image to video is in most cases the model of choice for Wan
+for the Text to Video Variant please read the description.
+Its also compatible
+Ratatoskr WAN 2.1 (ITV)
+and will for sure increase the quality especially in the NSFW Area.
+I also tested the I2V Lora with Wan 2.2 it seems to enhance the result too but very experimental
+Wan 2.2 I2V and T2V V1
+This enhancer version is for
+Wan 2.2
+its splitted in basically 2 Loras: low and high noise
+both loras for I2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+whats the pros of this lora compared to the wan 2.1?
+more consistent
+more specimen
+better in sfw and nsfw
+i recommend using both loras and use the workflow in the training folder Note: your resolution needed to set between 0.4 (480P) and 0.92 (720p) overwise the lora generate backscreens or other failures.
+for strength i prefer the full 1.0 strength its tested
+its tested with the original wan 2.2 model
+also in a short test with my
+Ratatoskr WAN 2.2 Hybrid v1.0 WIP
+model (use only the high noise version with that model)
+for technical data about Wan 2.2 visit there official site
+here:
+V2 Furry Enhancer High Noise
+Changes compared to V1
+more consistent
+more specimen
+better overall movements
+more stable overall
+way better with comic and anime than V1
+better in sfw and nsfw
+i recommend using the V1 Version of the
+WAN 2.2 I2V V1.0Low Noise
+Note: I used for example the old workflow for this model to compare V1 with V1 if you like the newest workflow download the training folder.
+Important for this workflow is to keep the resolution between 0.4 and 0.92 (480p - 720p)
+Making such loras take a huge amount of cost and time please support my work with a like.
+and please check out my other models and loras too ;-)
+made by
+freek22
+
+## Version Notes (WAN 2.2 T2V V1.0Low Noise)
+
+Low Noise Model
+This enhancer version is for Wan 2.2 T2V like the I2V its made for anthro / furry and fantasy creatures sfw and nsfw
+its splitted in basically 2 Loras: low and high noise
+both loras for T2V are trained on the same dataset. I its my own dataset before i trained with the wan 2.1 Lora but add more pictures and videos
+it's completely synthetic so no real persons or art is used for the dataset.
+i recommend using both loras in the video metadata there is a comfy workflow for using it.
+for the workflow all videos contain the workflows but i also packed the workflow in the "training" zip file.
+for this workflow i can recommend a step count between 8- 10 steps
+the model is only tested with the standard model and
+wan 2.2 lightning
+the model weight in all my testings was 1.0
+More information to wan 2.2 t2v you found
+here
+Note: this is V1 of this model so it sometimes still can fail also its very "spicy" and need for example descriptions for clothing
+Important:
+training such loras is very costly so if you like to support me please give a like and Check out my other models too.
+
+---
+
+## Civitai Links
+
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1782485?modelVersionId=2144527)**
+*   [View Full Model Page →](https://civitai.com/models/1782485)
+*   [View Creator Profile →](https://civitai.com/user/freek22)
+
+---
+
+## File Information
+
+*   **Filename**: `Furry Enhancer Wan2.2 V1 Low Noise .safetensors`
+*   **Size**: 585.09 MB
+*   **Hash (AutoV2)**: `5358231CDA`
+*   **Hash (SHA256)**: `5358231CDAB39132BAE7C5D6692E6F475FE82FCB2E4C3F56BC81CFA7E4A11626`

config.json

@@ -0,0 +1,4 @@
+{
+  "_comment": "Root config file...",
+  "model_type": "custom"
+}