https://huggingface.co/Teluv/Wan_Video_Burst_Effect
π Model Description (English)
Model Card: Wan_Video_Burst_Effect
π¨ Notice
This model is currently under R&D and in experimental training. The file may be unstable, but frequent updates with improved quality will be released soon.
Base Model: Wan2.2-T2V-A14B
Training Steps: 3000
Description
This LoRA model was trained for game asset Burst effect videos.
It specializes in generating consistent sprite-style Burst effects, making it suitable for 2D action games and idle RPGs.
Required Models
## Download Model
1-1. [Wan2.2-I2V-HighNoise](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors)
1-2. [Wan2.2-T2V-HighNoise](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors)
2-1. [Wan2.2-I2V-LowNoise](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors)
2-2. [Wan2.2-T2V-LowNoise](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors)
3. [Wan2.2-TextEncode](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)
4. [Wan2.2-HightNoise-Light-Lora](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors)
5. [Wan2.2-LowNoise-Light-Lora](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors)
6. [Wan2.1-Vae](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors)
π λͺ¨λΈ μ€λͺ (νκ΅μ΄)
λͺ¨λΈ μΉ΄λ: Wan_Video_Burst_Effect
π¨ μλ¦Ό
μ΄ λͺ¨λΈμ νμ¬ R&D κ³Όμ μμ μ€νμ μΌλ‘ νμ΅λ μνμ λλ€.
νμΌμ΄ λΆμμ ν μ μμΌλ©°, λΉ λ₯Έ μμΌ λ΄μ νλ¦¬ν° ν₯μ μ λ°μ΄νΈκ° μ 곡λ μμ μ λλ€.
λ² μ΄μ€ λͺ¨λΈ: Wan2.2-T2V-A14B
νμ΅ μ€ν μ: 3000
μ€λͺ
μ΄ LoRA λͺ¨λΈμ κ²μ μμ Burst μ΄ννΈ μμμ νΉνλμ΄ νμ΅λμμ΅λλ€.
μΌκ΄λ μ€νλΌμ΄νΈ μ€νμΌ Burst μ΄ννΈλ₯Ό μμ±ν μ μμΌλ©°, 2D μ‘μ κ²μ λ° λ°©μΉν RPG κ²μμ μ ν©ν©λλ€.
## Download Model
1-1. [Wan2.2-I2V-HighNoise](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_i2v_high_noise_14B_fp8_scaled.safetensors)
1-2. [Wan2.2-T2V-HighNoise](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/resolve/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp8_scaled.safetensors)
2-1. [Wan2.2-I2V-LowNoise](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_i2v_low_noise_14B_fp8_scaled.safetensors)
2-2. [Wan2.2-T2V-LowNoise](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp8_scaled.safetensors)
3. [Wan2.2-TextEncode](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors)
4. [Wan2.2-HightNoise-Light-Lora](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_high_noise.safetensors)
5. [Wan2.2-LowNoise-Light-Lora](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/loras/wan2.2_i2v_lightx2v_4steps_lora_v1_low_noise.safetensors)
6. [Wan2.1-Vae](https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors)
Description
FAQ
Comments (4)
nice
I don't know how the I2V is supposed to work. We're supposed to animate the effect first, then feed it that spritesheet as an image, then it just shows us our animation that we already made?
No! The sprite sheet is just an example I made separately. For I2V, you only need a single image to use as an effect.
@TeluvΒ Oh okay. I was confused, because your sprite sheets have full image gen prompts attached to them, and the videos have none. It looked like you want us to make the sprite sheets in Illustrious or something (since the prompting is in that style), then make the video using that. In fact, I still don't know how to prompt this because of that fact.
Your results look great though.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.