Sync 5 new model versions from Civitai (Batch 2/6)

Holi_Festival_of_Colors_WAN_by_Sarcastic_TOFU/Wan_Video_14B_i2v_480p/Holi_WAN_14b_I2V_v1.0.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e116e28edeef1f9cd4882c80f37531034c54bb309b16afca7c470ace05419bf8
+size 306807656

Lez_Make_Out/Wan_Video_14B_i2v_480p/l3z_kiss_i2v.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de8b62db2646ce1304613de21dff67b9491a3d28e188068bd79b36d33c4dd626
+size 359257680

Lightning_Lora_massive_speed_up_for_Wan2_1_Wan2_2_made_by_Lightx2v_Kijai/Wan_Video_14B_i2v_480p/Wan21_AccVid_I2V_480P_14B_lora_rank32_fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ea6f00472fc1ddf7c3a760fbfd6952ae488ecb73c9949804ccb71ea5841874
+size 322622176

Lightning_Lora_massive_speed_up_for_Wan2_1_Wan2_2_made_by_Lightx2v_Kijai/Wan_Video_14B_i2v_480p/Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64_fixed.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8833bd4fd7c8eabebf0bc8ee5cfaf47f4f310ce116928a02c1adf8941dd4b0f1
+size 739472104

Lightning_Lora_massive_speed_up_for_Wan2_1_Wan2_2_made_by_Lightx2v_Kijai/Wan_Video_14B_i2v_480p/lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c324ada09cfa447844f5d9a57240463a515de38270ef40c7513d74be3e64e72
+size 1466506280

README.md

@@ -44,5 +44,29 @@ A collection of models downloaded from Civitai. Click on a card to browse the fi
 <summary style="cursor: pointer; font-size: 0.9em; text-align: center; padding: 4px; border: 1px solid #d1d5db; border-radius: 6px;">View 4 More Previews</summary>
 <div style="padding-top: 8px;"><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/7998F638690D46359C0CE293534142837423005DF39868CB2093297A0B7269DB_214056a0.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/7998F638690D46359C0CE293534142837423005DF39868CB2093297A0B7269DB_c3cc2652.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/7998F638690D46359C0CE293534142837423005DF39868CB2093297A0B7269DB_1f3070b0.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/7998F638690D46359C0CE293534142837423005DF39868CB2093297A0B7269DB_c9bd5dad.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /></div>
 </details></div>
+<div style="display: flex; flex-direction: column;"><a href="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480p/tree/main/Holi_Festival_of_Colors_WAN_by_Sarcastic_TOFU" style="display: block; position: relative; width: 200px; height: 250px; border-radius: 8px; overflow: hidden; text-decoration: none; color: white; background-image: url('https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_9c3fde5f.jpg'); background-size: cover; background-position: center; box-shadow: 0 4px 6px -1px rgba(0,0,0,0.1);">
+<div style="position: absolute; top: 0; left: 0; right: 0; bottom: 0; background: linear-gradient(to top, rgba(0,0,0,0.85) 0%, rgba(0,0,0,0) 60%); display: flex; flex-direction: column; justify-content: flex-end; padding: 12px; text-align: left;">
+<h3 style="margin: 0; font-size: 1.1em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">Holi_Festival_of_Colors_WAN_by_Sarcastic_TOFU</h3>
+<p style="margin: 4px 0 0 0; font-size: 0.9em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">sarcastictofu</p>
+</div>
+</a><details style="width: 200px; margin-top: 8px;">
+<summary style="cursor: pointer; font-size: 0.9em; text-align: center; padding: 4px; border: 1px solid #d1d5db; border-radius: 6px;">View 8 More Previews</summary>
+<div style="padding-top: 8px;"><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_5a5e0bf4.jpg" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_05283c25.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_ca0de38b.jpg" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_2c07063e.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_6bb6d23b.jpg" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_8c362cea.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_a9e5eb29.jpg" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8_d5aaf4ce.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /></div>
+</details></div>
+<div style="display: flex; flex-direction: column;"><a href="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480p/tree/main/Lez_Make_Out" style="display: block; position: relative; width: 200px; height: 250px; border-radius: 8px; overflow: hidden; text-decoration: none; color: white; background-image: url('https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/DE8B62DB2646CE1304613DE21DFF67B9491A3D28E188068BD79B36D33C4DD626_50855bab.gif'); background-size: cover; background-position: center; box-shadow: 0 4px 6px -1px rgba(0,0,0,0.1);">
+<div style="position: absolute; top: 0; left: 0; right: 0; bottom: 0; background: linear-gradient(to top, rgba(0,0,0,0.85) 0%, rgba(0,0,0,0) 60%); display: flex; flex-direction: column; justify-content: flex-end; padding: 12px; text-align: left;">
+<h3 style="margin: 0; font-size: 1.1em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">Lez Make Out</h3>
+<p style="margin: 4px 0 0 0; font-size: 0.9em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">jalenbrunson</p>
+</div>
+</a></div>
+<div style="display: flex; flex-direction: column;"><a href="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480p/tree/main/Lightning_Lora_massive_speed_up_for_Wan2_1_Wan2_2_made_by_Lightx2v_Kijai" style="display: block; position: relative; width: 200px; height: 250px; border-radius: 8px; overflow: hidden; text-decoration: none; color: white; background-image: url('https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/8833BD4FD7C8EABEBF0BC8EE5CFAF47F4F310CE116928A02C1ADF8941DD4B0F1_016a1009.gif'); background-size: cover; background-position: center; box-shadow: 0 4px 6px -1px rgba(0,0,0,0.1);">
+<div style="position: absolute; top: 0; left: 0; right: 0; bottom: 0; background: linear-gradient(to top, rgba(0,0,0,0.85) 0%, rgba(0,0,0,0) 60%); display: flex; flex-direction: column; justify-content: flex-end; padding: 12px; text-align: left;">
+<h3 style="margin: 0; font-size: 1.1em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">Lightning Lora, massive speed up for Wan2.1 / Wan2.2 made by Lightx2v / Kijai</h3>
+<p style="margin: 4px 0 0 0; font-size: 0.9em; text-shadow: 1px 1px 3px rgba(0,0,0,0.8);">Ada321</p>
+</div>
+</a><details style="width: 200px; margin-top: 8px;">
+<summary style="cursor: pointer; font-size: 0.9em; text-align: center; padding: 4px; border: 1px solid #d1d5db; border-radius: 6px;">View 2 More Previews</summary>
+<div style="padding-top: 8px;"><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/8833BD4FD7C8EABEBF0BC8EE5CFAF47F4F310CE116928A02C1ADF8941DD4B0F1_a288cadb.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /><img src="https://huggingface.co/UnifiedHorusRA/TheWan2.1I2V480pclass/resolve/main/8833BD4FD7C8EABEBF0BC8EE5CFAF47F4F310CE116928A02C1ADF8941DD4B0F1_7aa7022a.gif" style="width: 100%; margin-top: 8px; border-radius: 4px;" /></div>
+</details></div>
 <!--CIVITAI_MODEL_GALLERY_END-->
 </div>

Wan_Video_14B_i2v_480p_info.md

@@ -164,4 +164,241 @@ No nice blowjobs here. She's gagging on this rough deepthroat, made for both two
 *   **Size**: 292.63 MB
 *   **Hash (AutoV2)**: `7998F63869`
 *   **Hash (SHA256)**: `7998F638690D46359C0CE293534142837423005DF39868CB2093297A0B7269DB`
+---
+
+---
+# Holi_Festival_of_Colors_WAN_by_Sarcastic_TOFU (Version: Holi_WAN_14bI2V_v1.0)
+**Creator**: [sarcastictofu](https://civitai.com/user/sarcastictofu)
+**Type**: LORA
+**Base Model**: Wan Video 14B i2v 480p
+**Version Uploaded**: 2025-09-26
+**Trigger Words**: `Festival_of_Colors`
+**Civitai Model ID**: 1880137
+**Civitai Version ID**: 2253158
+**Stats (at time of fetch for this version)**:
+*   Downloads: 43
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## 📄 Description (Parent Model)
+Holi (the festival of colors) celebrates the beginning of spring and the victory of good over evil according to traditional Indian lunar calendar system. This is held on the last full-moon day of the lunar month, the festival sees people smearing bright colors on Indian and South Asian communities inside and outside India. This LORA delivers the colorful essence of Holi in your AI generation. It can produce both SFW & NSFW outputs and depending on your base model and prompting style you may more or less frequently come across NSFW output so use this LORA with care.
+To use this LORA you may simply use the following trigger words -
+Festival_of_Colors
+## Civitai Links
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1880137?modelVersionId=2253158)**
+*   [View Full Model Page →](https://civitai.com/models/1880137)
+*   [View Creator Profile →](https://civitai.com/user/sarcastictofu)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `Holi_WAN_14b_I2V_v1.0.safetensors`
+*   **Size**: 292.59 MB
+*   **Hash (AutoV2)**: `E116E28EDE`
+*   **Hash (SHA256)**: `E116E28EDEEF1F9CD4882C80F37531034C54BB309B16AFCA7C470ACE05419BF8`
+---
+
+---
+# Lez Make Out (Version: I2V)
+**Creator**: [jalenbrunson](https://civitai.com/user/jalenbrunson)
+**Type**: LORA
+**Base Model**: Wan Video 14B i2v 480p
+**Version Uploaded**: 2025-05-15
+**Trigger Words**: `l3z_kiss`
+**Civitai Model ID**: 1392031
+**Civitai Version ID**: 1792573
+**Stats (at time of fetch for this version)**:
+*   Downloads: 4477
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## 📄 Description (Parent Model)
+Lesbian make out session, trained on 52 videos from the same video series. Two models for I2V/T2V 14B..
+The prompt: 2 women making out, 2 women tongue kissing, l3z_kiss.
+I use strength 1.0 for the I2V model and the faces don't change..
+Under suggested resources I list hearmeman’s workflows. I use his runpod templates for training and workflows - highly recommend. I also recommend the combine 2 character Lora flux workflow which can give you an amazing starting picture. I’ve been trying to train multi-character Loras with no success, so this is the next best thing.
+## Civitai Links
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1392031?modelVersionId=1792573)**
+*   [View Full Model Page →](https://civitai.com/models/1392031)
+*   [View Creator Profile →](https://civitai.com/user/jalenbrunson)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `l3z_kiss_i2v.safetensors`
+*   **Size**: 342.61 MB
+*   **Hash (AutoV2)**: `DE8B62DB26`
+*   **Hash (SHA256)**: `DE8B62DB2646CE1304613DE21DFF67B9491A3D28E188068BD79B36D33C4DD626`
+---
+
+---
+# Lightning Lora, massive speed up for Wan2.1 / Wan2.2 made by Lightx2v / Kijai (Version: Self-Forcing 14B I2V)
+**Creator**: [Ada321](https://civitai.com/user/Ada321)
+**Type**: LORA
+**Base Model**: Wan Video 14B i2v 480p
+**Version Uploaded**: 2025-07-16
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 1585622
+**Civitai Version ID**: 2014449
+**Stats (at time of fetch for this version)**:
+*   Downloads: 12232
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## 📄 Description (Parent Model)
+2.2
+New I2V 1022 versions are out. They have by far the best prompt following / motion quality yet. (The lora key warning is fine, it just contains extra modulation keys that comfyui does not use. It does not matter.)
+https://github.com/VraethrDalkr/ComfyUI-TripleKSampler
+T2V versions just got updated 09/28. Probably still best to use a step or two with cfg / without the lora to establish motion with high noise as usual like:
+2 steps high noise without the low-step lora at 3.5 CFG
+2 steps high noise with lora and 1 CFG
+2-4 steps low noise with lora and 1 CFG
+Its definitely a big improvement either way.
+T2V:
+Using their full 'dyno' model for your high model seems best.
+"On Sep 28, 2025, we released two models, Wan2.2-T2V-A14B-4steps-lora-250928 and Wan2.2-T2V-A14B-4steps-250928-dyno. The two models share the same low-noise weight. Wan2.2-T2V-A14B-4steps-250928-dyno delivers superior motion rendering and camera response, with object movement speeds that closely match those of the base model. For projects requiring highly dynamic visuals, we strongly recommend using Wan2.2-T2V-A14B-4steps-250928-dyno. Below, you will find some showcases for reference."
+https://huggingface.co/lightx2v/Wan2.2-Lightning/blob/main/Wan2.2-T2V-A14B-4steps-250928-dyno/Wan2.2-T2V-A14B-4steps-250928-dyno-high-lightx2v.safetensors
+2.1
+7/15 update: I added the new I2V lora, seems to have much better motion than using the old text to video lora on a image to video model. Example is 4 steps, 1 CFG, LCM sampler, 8 shift. I uploaded the new version of the T2V one also.
+I'm also putting up the rank 128 versions extracted by Kijai, they are double the size but are slightly better quality.
+I suggest using it with the Pusa V1 lora as well, it seems to improve movement even more:
+https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Pusa
+No need for 2 sampler WF anymore IMO. Just plug it into your normal WF with 1 CFG and 4 steps or so. Could prob sharpen it with another pass if you wanted but it no longer hurts the movement like before for image to video.
+Full Image to video Lightx2V model:
+https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/tree/main/distill_models
+Old:
+lightx2v
+made a 14B self forcing model that is a massive improvement compared to Causvid / Accvid. Kijai extracted it as a
+lora
+. Example above was generated in about 35 seconds on a 4090 using 4 steps, lcm, 1 cfg, 8 shift, still playing with settings to see what is best.
+Please don't send me buzz or anything, give the
+lightx2v
+team or
+kijai
+support if anyone.
+## Civitai Links
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1585622?modelVersionId=2014449)**
+*   [View Full Model Page →](https://civitai.com/models/1585622)
+*   [View Creator Profile →](https://civitai.com/user/Ada321)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64_fixed.safetensors`
+*   **Size**: 705.22 MB
+*   **Hash (AutoV2)**: `8833BD4FD7`
+*   **Hash (SHA256)**: `8833BD4FD7C8EABEBF0BC8EE5CFAF47F4F310CE116928A02C1ADF8941DD4B0F1`
+---
+
+---
+# Lightning Lora, massive speed up for Wan2.1 / Wan2.2 made by Lightx2v / Kijai (Version: Accvid 14B I2V)
+**Creator**: [Ada321](https://civitai.com/user/Ada321)
+**Type**: LORA
+**Base Model**: Wan Video 14B i2v 480p
+**Version Uploaded**: 2025-06-05
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 1585622
+**Civitai Version ID**: 1871541
+**Stats (at time of fetch for this version)**:
+*   Downloads: 2430
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## 📄 Description (Parent Model)
+2.2
+New I2V 1022 versions are out. They have by far the best prompt following / motion quality yet. (The lora key warning is fine, it just contains extra modulation keys that comfyui does not use. It does not matter.)
+https://github.com/VraethrDalkr/ComfyUI-TripleKSampler
+T2V versions just got updated 09/28. Probably still best to use a step or two with cfg / without the lora to establish motion with high noise as usual like:
+2 steps high noise without the low-step lora at 3.5 CFG
+2 steps high noise with lora and 1 CFG
+2-4 steps low noise with lora and 1 CFG
+Its definitely a big improvement either way.
+T2V:
+Using their full 'dyno' model for your high model seems best.
+"On Sep 28, 2025, we released two models, Wan2.2-T2V-A14B-4steps-lora-250928 and Wan2.2-T2V-A14B-4steps-250928-dyno. The two models share the same low-noise weight. Wan2.2-T2V-A14B-4steps-250928-dyno delivers superior motion rendering and camera response, with object movement speeds that closely match those of the base model. For projects requiring highly dynamic visuals, we strongly recommend using Wan2.2-T2V-A14B-4steps-250928-dyno. Below, you will find some showcases for reference."
+https://huggingface.co/lightx2v/Wan2.2-Lightning/blob/main/Wan2.2-T2V-A14B-4steps-250928-dyno/Wan2.2-T2V-A14B-4steps-250928-dyno-high-lightx2v.safetensors
+2.1
+7/15 update: I added the new I2V lora, seems to have much better motion than using the old text to video lora on a image to video model. Example is 4 steps, 1 CFG, LCM sampler, 8 shift. I uploaded the new version of the T2V one also.
+I'm also putting up the rank 128 versions extracted by Kijai, they are double the size but are slightly better quality.
+I suggest using it with the Pusa V1 lora as well, it seems to improve movement even more:
+https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Pusa
+No need for 2 sampler WF anymore IMO. Just plug it into your normal WF with 1 CFG and 4 steps or so. Could prob sharpen it with another pass if you wanted but it no longer hurts the movement like before for image to video.
+Full Image to video Lightx2V model:
+https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/tree/main/distill_models
+Old:
+lightx2v
+made a 14B self forcing model that is a massive improvement compared to Causvid / Accvid. Kijai extracted it as a
+lora
+. Example above was generated in about 35 seconds on a 4090 using 4 steps, lcm, 1 cfg, 8 shift, still playing with settings to see what is best.
+Please don't send me buzz or anything, give the
+lightx2v
+team or
+kijai
+support if anyone.
+## Civitai Links
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1585622?modelVersionId=1871541)**
+*   [View Full Model Page →](https://civitai.com/models/1585622)
+*   [View Creator Profile →](https://civitai.com/user/Ada321)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `Wan21_AccVid_I2V_480P_14B_lora_rank32_fp16.safetensors`
+*   **Size**: 307.68 MB
+*   **Hash (AutoV2)**: `36EA6F0047`
+*   **Hash (SHA256)**: `36EA6F00472FC1DDF7C3A760FBFD6952AE488ECB73C9949804CCB71EA5841874`
+---
+
+---
+# Lightning Lora, massive speed up for Wan2.1 / Wan2.2 made by Lightx2v / Kijai (Version: Self-Forcing 14B I2V R128)
+**Creator**: [Ada321](https://civitai.com/user/Ada321)
+**Type**: LORA
+**Base Model**: Wan Video 14B i2v 480p
+**Version Uploaded**: 2025-07-16
+**Trigger Words**: `N/A`
+**Civitai Model ID**: 1585622
+**Civitai Version ID**: 2016546
+**Stats (at time of fetch for this version)**:
+*   Downloads: 3046
+*   Rating: 0.0 (0 ratings)
+*   Favorites: N/A
+---
+## 📄 Description (Parent Model)
+2.2
+New I2V 1022 versions are out. They have by far the best prompt following / motion quality yet. (The lora key warning is fine, it just contains extra modulation keys that comfyui does not use. It does not matter.)
+https://github.com/VraethrDalkr/ComfyUI-TripleKSampler
+T2V versions just got updated 09/28. Probably still best to use a step or two with cfg / without the lora to establish motion with high noise as usual like:
+2 steps high noise without the low-step lora at 3.5 CFG
+2 steps high noise with lora and 1 CFG
+2-4 steps low noise with lora and 1 CFG
+Its definitely a big improvement either way.
+T2V:
+Using their full 'dyno' model for your high model seems best.
+"On Sep 28, 2025, we released two models, Wan2.2-T2V-A14B-4steps-lora-250928 and Wan2.2-T2V-A14B-4steps-250928-dyno. The two models share the same low-noise weight. Wan2.2-T2V-A14B-4steps-250928-dyno delivers superior motion rendering and camera response, with object movement speeds that closely match those of the base model. For projects requiring highly dynamic visuals, we strongly recommend using Wan2.2-T2V-A14B-4steps-250928-dyno. Below, you will find some showcases for reference."
+https://huggingface.co/lightx2v/Wan2.2-Lightning/blob/main/Wan2.2-T2V-A14B-4steps-250928-dyno/Wan2.2-T2V-A14B-4steps-250928-dyno-high-lightx2v.safetensors
+2.1
+7/15 update: I added the new I2V lora, seems to have much better motion than using the old text to video lora on a image to video model. Example is 4 steps, 1 CFG, LCM sampler, 8 shift. I uploaded the new version of the T2V one also.
+I'm also putting up the rank 128 versions extracted by Kijai, they are double the size but are slightly better quality.
+I suggest using it with the Pusa V1 lora as well, it seems to improve movement even more:
+https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Pusa
+No need for 2 sampler WF anymore IMO. Just plug it into your normal WF with 1 CFG and 4 steps or so. Could prob sharpen it with another pass if you wanted but it no longer hurts the movement like before for image to video.
+Full Image to video Lightx2V model:
+https://huggingface.co/lightx2v/Wan2.1-I2V-14B-480P-StepDistill-CfgDistill-Lightx2v/tree/main/distill_models
+Old:
+lightx2v
+made a 14B self forcing model that is a massive improvement compared to Causvid / Accvid. Kijai extracted it as a
+lora
+. Example above was generated in about 35 seconds on a 4090 using 4 steps, lcm, 1 cfg, 8 shift, still playing with settings to see what is best.
+Please don't send me buzz or anything, give the
+lightx2v
+team or
+kijai
+support if anyone.
+## Civitai Links
+*   **[🔗 View This Version on Civitai →](https://civitai.com/models/1585622?modelVersionId=2016546)**
+*   [View Full Model Page →](https://civitai.com/models/1585622)
+*   [View Creator Profile →](https://civitai.com/user/Ada321)
+---
+## File Information
+
+*   **Primary Filename (Civitai)**: `lightx2v_I2V_14B_480p_cfg_step_distill_rank128_bf16.safetensors`
+*   **Size**: 1398.57 MB
+*   **Hash (AutoV2)**: `5C324ADA09`
+*   **Hash (SHA256)**: `5C324ADA09CFA447844F5D9A57240463A515DE38270EF40C7513D74BE3E64E72`
 ---

civitai_tracker.json

@@ -29,6 +29,26 @@
       "versions": [
         "2239474"
       ]
+    },
+    "1880137": {
+      "name": "Holi_Festival_of_Colors_WAN_by_Sarcastic_TOFU",
+      "versions": [
+        "2253158"
+      ]
+    },
+    "1392031": {
+      "name": "Lez Make Out",
+      "versions": [
+        "1792573"
+      ]
+    },
+    "1585622": {
+      "name": "Lightning Lora, massive speed up for Wan2.1 / Wan2.2 made by Lightx2v / Kijai",
+      "versions": [
+        "2014449",
+        "1871541",
+        "2016546"
+      ]
     }
   },
   "versions": [
@@ -36,6 +56,11 @@
     "1870287",
     "2018238",
     "2263107",
-    "2239474"
+    "2239474",
+    "2253158",
+    "1792573",
+    "2014449",
+    "1871541",
+    "2016546"
   ]
 }